TOP ACTIVATIONS
MAX = 29.507

it wouldn 't get wrink led . She took her time
so happy that she whist led all the way home .
As he padd led along , he saw an
silver ware until it spark led . Tim my 's mom
she did , it spark led with the most beautiful light
a shiny rock that spark led in the sun . She
S ara gigg led . She picked up her
The boy sc ow led and said , " Well
graceful car - it spark led in the sunshine . One
looked at them and grow led again . Tom and Lily
Dad r uff led his hair and said ,
much that she quickly tid ied up her room . Her
Suddenly , his mom tick led him and he laughed and
. But it tw ink led in the sunlight and danced
Henry gigg led and followed the cat .
, Bob 's eyes spark led with joy . His sister
fancy crystal necklace that spark led in the sun . One
the wind as it rust led through the leaves .
The cater pillar w igg led inside and felt safe .
led as the popcorn tick led her . Am

MIN ACTIVATIONS
MIN = -24.207

- to always share and think of others ! <|endoftext|> Once
looked around and tried to think of something . Suddenly she
disagreed , they tried to think of solutions . That way
surprised since he didn 't think his family could be competitive
her chin . " I think the gorilla must be rich
his bicycle and tried to think of ways to get better
, but he couldn 't think of anything special to give
bored . He couldn 't think of anything to do .
. He could speak and think in ways that other caul
" Be smart and always think before you make a decision
rep lying , " I think it 's a boun cy
, saying , " I think I know where your umbrella
got it today ! I think it would be perfect for
all , she couldn 't think of anything good . Everything
of it . Molly would think a lot about her team
asked , " Do you think it wants to play ?"
Mr . Dragon . I think you 're cool ." The
la ! What do you think that is ?" Kay la
, so she couldn 't think of a good idea .
then said , " I think I can help ."

INTERVAL 16.078 - 29.507
CONTAINS 0.384%

went to Sue and bark ed . Sue knew what Spot
Can I have the t eddy bear , L ila ?"
because she loved her t eddy bear very much .
Her mom smiled and c uddled her too . They were
explore ." L ily did not want to go

INTERVAL 2.650 - 16.078
CONTAINS 37.025%

together for a long time . They were all very happy
it a marble ?" Ben asked . " No
all about the mysterious math book . The
The spring jumped out of the teaspoon and went very high
of his room , talking in quiet voices . They were

INTERVAL -10.778 - 2.650
CONTAINS 59.397%

her hands and crossed the street to get to the park
went away , and the little car drove out of the
ily says , " OK , Tom . But don 't
Mike had to act fast . He grabbed a tall
them . She said , " It 's so great that

INTERVAL -24.207 - -10.778
CONTAINS 3.194%

know what to expect . But her mom my held her
day , Lucy would take care of the da isy .
some more pretty pictures . The End .
and showed them how to count it .
that your snow men are not food . He knows that
Token it
Token ID340
Feature activation-1.03e+00

Pos logit contributions
 pleasure+0.273
 Deal+0.246
 welcome+0.195
 learn+0.193
 OK+0.184
Neg logit contributions
led-0.524
ed-0.440
ied-0.399
y-0.390
ling-0.386
Token wouldn
Token ID3636
Feature activation+8.11e+00

Pos logit contributions
 pleasure+0.059
 think+0.052
 know+0.050
 learn+0.050
 welcome+0.050
Neg logit contributions
led-0.062
ed-0.049
ied-0.046
we-0.043
ing-0.043
Token't
Token ID470
Feature activation-2.01e-01

Pos logit contributions
led+0.721
ed+0.636
y+0.568
ied+0.567
les+0.556
Neg logit contributions
 pleasure-0.296
 Deal-0.242
 welcome-0.196
 learn-0.176
 think-0.173
Token get
Token ID651
Feature activation-8.14e+00

Pos logit contributions
 pleasure+0.008
 Deal+0.007
 welcome+0.005
 Not+0.005
 learn+0.005
Neg logit contributions
led-0.017
ed-0.015
y-0.014
ied-0.013
ling-0.013
Token wrink
Token ID34866
Feature activation+8.03e+00

Pos logit contributions
 pleasure+0.444
 Deal+0.365
 welcome+0.361
 OK+0.352
 great+0.341
Neg logit contributions
led-0.582
ed-0.476
ied-0.422
y-0.421
les-0.414
Tokenled
Token ID992
Feature activation+2.68e+01

Pos logit contributions
led+0.187
ed+0.113
we+0.098
ied+0.089
web+0.089
Neg logit contributions
 pleasure-0.704
 Deal-0.655
 OK-0.634
 great-0.631
 welcome-0.630
Token.
Token ID13
Feature activation+6.98e+00

Pos logit contributions
led+1.936
ed+1.586
ied+1.420
y+1.366
les+1.350
Neg logit contributions
 pleasure-1.467
 Deal-1.252
 welcome-1.182
 OK-1.127
 think-1.119
Token She
Token ID1375
Feature activation+4.22e+00

Pos logit contributions
led+0.560
ed+0.507
y+0.450
ied+0.440
ted+0.437
Neg logit contributions
 pleasure-0.266
 Deal-0.224
 learn-0.193
 welcome-0.190
 great-0.181
Token took
Token ID1718
Feature activation+9.10e+00

Pos logit contributions
led+0.272
ed+0.220
ied+0.194
y+0.189
ing+0.185
Neg logit contributions
 pleasure-0.254
 Deal-0.229
 think-0.211
 learn-0.209
 welcome-0.208
Token her
Token ID607
Feature activation+3.77e+00

Pos logit contributions
led+0.745
ed+0.636
ied+0.569
y+0.559
les+0.548
Neg logit contributions
 pleasure-0.406
 Deal-0.353
 welcome-0.303
 learn-0.290
 think-0.285
Token time
Token ID640
Feature activation-8.36e+00

Pos logit contributions
led+0.292
ed+0.245
ied+0.219
y+0.216
les+0.210
Neg logit contributions
 pleasure-0.186
 Deal-0.161
 welcome-0.143
 learn-0.137
 think-0.136
Token so
Token ID523
Feature activation-6.30e+00

Pos logit contributions
 pleasure+0.091
 Deal+0.072
 welcome+0.058
 learn+0.052
 think+0.052
Neg logit contributions
led-0.253
ed-0.221
ied-0.202
y-0.201
les-0.196
Token happy
Token ID3772
Feature activation-8.28e+00

Pos logit contributions
 pleasure+0.273
 Deal+0.246
 welcome+0.195
 learn+0.193
 OK+0.184
Neg logit contributions
led-0.524
ed-0.440
ied-0.399
y-0.390
ling-0.386
Token that
Token ID326
Feature activation+3.67e+00

Pos logit contributions
 pleasure+0.442
 welcome+0.362
 Deal+0.348
 think+0.346
 learn+0.341
Neg logit contributions
led-0.587
ed-0.473
ied-0.435
med-0.416
ling-0.412
Token she
Token ID673
Feature activation+6.74e+00

Pos logit contributions
led+0.256
ed+0.211
ied+0.186
y+0.184
les+0.177
Neg logit contributions
 pleasure-0.206
 Deal-0.185
 welcome-0.163
 learn-0.159
 think-0.157
Token whist
Token ID32262
Feature activation+4.88e+00

Pos logit contributions
led+0.417
ed+0.331
ied+0.306
y+0.297
ing+0.288
Neg logit contributions
 pleasure-0.414
 welcome-0.350
 Deal-0.349
 think-0.347
 learn-0.343
Tokenled
Token ID992
Feature activation+2.65e+01

Pos logit contributions
led+0.023
ed-0.020
we-0.031
ied-0.033
ted-0.041
Neg logit contributions
 pleasure-0.500
 great-0.471
 Deal-0.467
 welcome-0.463
 learn-0.456
Token all
Token ID477
Feature activation+1.16e-01

Pos logit contributions
led+1.903
ed+1.571
ied+1.384
y+1.373
les+1.328
Neg logit contributions
 pleasure-1.443
 Deal-1.280
 welcome-1.144
 learn-1.106
 think-1.091
Token the
Token ID262
Feature activation+3.90e+00

Pos logit contributions
led+0.009
ed+0.008
ied+0.007
awed+0.007
we+0.007
Neg logit contributions
 pleasure-0.005
 welcome-0.004
 Deal-0.004
 learn-0.004
 great-0.004
Token way
Token ID835
Feature activation-9.21e+00

Pos logit contributions
led+0.342
ed+0.291
ied+0.265
y+0.264
les+0.259
Neg logit contributions
 pleasure-0.150
 Deal-0.128
 welcome-0.106
 learn-0.101
 know-0.099
Token home
Token ID1363
Feature activation-7.32e+00

Pos logit contributions
 pleasure+0.543
 welcome+0.450
 Deal+0.437
 learn+0.428
 OK+0.419
Neg logit contributions
led-0.617
ed-0.481
awed-0.416
ied-0.415
ils-0.410
Token.
Token ID13
Feature activation+6.37e+00

Pos logit contributions
 pleasure+0.418
 welcome+0.345
 learn+0.343
 Deal+0.334
 great+0.326
Neg logit contributions
led-0.498
ed-0.387
ied-0.353
awed-0.347
les-0.345
Token
Token ID198
Feature activation-4.90e+00

Pos logit contributions
 pleasure+0.143
 Deal+0.131
 Today+0.105
 welcome+0.105
 Not+0.100
Neg logit contributions
led-0.239
ed-0.203
y-0.176
ied-0.176
ted-0.172
Token
Token ID198
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.242
 Deal+0.186
 deal+0.171
 welcome+0.162
 great+0.158
Neg logit contributions
led-0.358
ed-0.306
y-0.289
ied-0.279
med-0.276
TokenAs
Token ID1722
Feature activation-3.92e+00

Pos logit contributions
 pleasure+0.351
 Deal+0.286
 welcome+0.259
 deal+0.253
 opinion+0.248
Neg logit contributions
led-0.369
ed-0.307
y-0.289
ied-0.278
we-0.274
Token he
Token ID339
Feature activation+7.51e+00

Pos logit contributions
 pleasure+0.216
 Deal+0.195
 welcome+0.170
 learn+0.165
 think+0.163
Neg logit contributions
led-0.277
ed-0.229
y-0.203
ied-0.202
les-0.193
Token padd
Token ID14098
Feature activation+5.70e+00

Pos logit contributions
led+0.480
ed+0.383
ied+0.347
ling+0.329
ier+0.328
Neg logit contributions
 pleasure-0.445
 Deal-0.385
 think-0.372
 learn-0.372
 welcome-0.368
Tokenled
Token ID992
Feature activation+2.64e+01

Pos logit contributions
we+0.012
led+0.010
ed-0.029
web-0.031
pled-0.040
Neg logit contributions
 pleasure-0.561
 welcome-0.536
 know-0.530
 think-0.526
 learn-0.522
Token along
Token ID1863
Feature activation+9.90e+00

Pos logit contributions
led+1.864
ed+1.533
ied+1.341
y+1.335
ling+1.291
Neg logit contributions
 pleasure-1.485
 Deal-1.330
 welcome-1.180
 learn-1.139
 OK-1.120
Token,
Token ID11
Feature activation-4.36e+00

Pos logit contributions
led+0.796
ed+0.668
ied+0.603
y+0.594
les+0.580
Neg logit contributions
 pleasure-0.458
 Deal-0.388
 welcome-0.350
 learn-0.334
 think-0.329
Token he
Token ID339
Feature activation+5.92e+00

Pos logit contributions
 pleasure+0.245
 Deal+0.218
 welcome+0.195
 learn+0.189
 think+0.186
Neg logit contributions
led-0.306
ed-0.251
ied-0.220
y-0.218
les-0.211
Token saw
Token ID2497
Feature activation+2.55e+00

Pos logit contributions
led+0.367
ed+0.291
ied+0.260
y+0.247
we+0.239
Neg logit contributions
 pleasure-0.368
 Deal-0.323
 learn-0.308
 think-0.307
 welcome-0.303
Token an
Token ID281
Feature activation-2.98e+00

Pos logit contributions
led+0.234
ed+0.199
ied+0.185
y+0.185
les+0.179
Neg logit contributions
 pleasure-0.087
 Deal-0.064
 welcome-0.059
 learn-0.055
 great-0.054
Token silver
Token ID8465
Feature activation+8.91e+00

Pos logit contributions
led+0.483
ed+0.405
ied+0.368
y+0.365
les+0.357
Neg logit contributions
 pleasure-0.264
 Deal-0.231
 welcome-0.196
 learn-0.189
 OK-0.185
Tokenware
Token ID1574
Feature activation+1.80e+01

Pos logit contributions
led+0.641
ed+0.519
ied+0.471
med+0.458
awed+0.450
Neg logit contributions
 pleasure-0.463
 welcome-0.360
 learn-0.348
 great-0.347
 think-0.345
Token until
Token ID1566
Feature activation-6.70e+00

Pos logit contributions
led+1.205
ed+0.939
awed+0.878
ied+0.872
ling+0.870
Neg logit contributions
 pleasure-0.998
 welcome-0.826
 think-0.794
 Deal-0.785
 learn-0.775
Token it
Token ID340
Feature activation-2.68e+00

Pos logit contributions
 pleasure+0.320
 Deal+0.271
 welcome+0.245
 learn+0.235
 think+0.232
Neg logit contributions
led-0.529
ed-0.442
ied-0.397
y-0.394
ling-0.386
Token spark
Token ID9009
Feature activation+5.51e+00

Pos logit contributions
 pleasure+0.143
 Deal+0.120
 great+0.116
 welcome+0.115
 think+0.115
Neg logit contributions
led-0.184
ed-0.146
ied-0.137
we-0.131
ling-0.129
Tokenled
Token ID992
Feature activation+2.63e+01

Pos logit contributions
led+0.033
ied+0.005
we+0.000
web-0.002
awed-0.010
Neg logit contributions
 pleasure-0.520
 great-0.492
 fun-0.463
 think-0.462
 name-0.461
Token.
Token ID13
Feature activation+6.64e+00

Pos logit contributions
led+1.731
ed+1.401
ied+1.258
awed+1.214
we+1.203
Neg logit contributions
 pleasure-1.587
 welcome-1.317
 great-1.272
 Deal-1.269
 OK-1.249
Token Tim
Token ID5045
Feature activation-2.16e+00

Pos logit contributions
led+0.538
ed+0.487
y+0.436
ied+0.427
med+0.423
Neg logit contributions
 pleasure-0.250
 Deal-0.211
 learn-0.178
 welcome-0.178
 great-0.172
Tokenmy
Token ID1820
Feature activation-2.50e+00

Pos logit contributions
 pleasure+0.113
 Deal+0.097
 think+0.092
 learn+0.091
 welcome+0.091
Neg logit contributions
led-0.156
ed-0.128
ied-0.115
we-0.110
ier-0.110
Token's
Token ID338
Feature activation+5.44e+00

Pos logit contributions
 pleasure+0.146
 Deal+0.127
 think+0.122
 learn+0.121
 know+0.121
Neg logit contributions
led-0.163
ed-0.132
ied-0.117
ier-0.112
we-0.110
Token mom
Token ID1995
Feature activation-5.63e+00

Pos logit contributions
led+0.467
ed+0.401
ied+0.365
y+0.363
les+0.352
Neg logit contributions
 pleasure-0.203
 Deal-0.184
 welcome-0.151
 learn-0.144
 know-0.141
Token she
Token ID673
Feature activation+9.74e+00

Pos logit contributions
led+0.750
ed+0.625
ied+0.572
awed+0.563
y+0.548
Neg logit contributions
 pleasure-0.413
 welcome-0.327
 Deal-0.327
 great-0.315
 think-0.306
Token did
Token ID750
Feature activation+5.98e+00

Pos logit contributions
led+0.608
ed+0.482
ied+0.430
y+0.417
ing+0.410
Neg logit contributions
 pleasure-0.607
 Deal-0.531
 welcome-0.508
 think-0.501
 learn-0.498
Token,
Token ID11
Feature activation-2.77e+00

Pos logit contributions
led+0.473
ed+0.402
ied+0.362
y+0.360
les+0.350
Neg logit contributions
 pleasure-0.277
 Deal-0.243
 welcome-0.201
 OK-0.182
 Today-0.177
Token it
Token ID340
Feature activation-2.29e+00

Pos logit contributions
 pleasure+0.144
 Deal+0.128
 welcome+0.112
 learn+0.107
 know+0.105
Neg logit contributions
led-0.204
ed-0.170
y-0.151
ied-0.150
les-0.145
Token spark
Token ID9009
Feature activation+5.74e+00

Pos logit contributions
 pleasure+0.120
 think+0.107
 learn+0.104
 Deal+0.102
 great+0.102
Neg logit contributions
led-0.151
ed-0.123
ied-0.116
ing-0.107
awed-0.106
Tokenled
Token ID992
Feature activation+2.63e+01

Pos logit contributions
led+0.040
ied+0.017
we+0.003
year+0.001
web-0.003
Neg logit contributions
 pleasure-0.522
 great-0.502
 fun-0.483
 think-0.482
 know-0.469
Token with
Token ID351
Feature activation+2.63e+00

Pos logit contributions
led+1.877
ed+1.540
ied+1.402
les+1.338
we+1.324
Neg logit contributions
 pleasure-1.449
 Deal-1.198
 welcome-1.180
 great-1.116
 OK-1.103
Token the
Token ID262
Feature activation+3.91e+00

Pos logit contributions
led+0.228
ed+0.195
ied+0.176
y+0.175
les+0.171
Neg logit contributions
 pleasure-0.102
 Deal-0.089
 welcome-0.073
 learn-0.070
 think-0.068
Token most
Token ID749
Feature activation-6.62e+00

Pos logit contributions
led+0.289
ed+0.240
ied+0.212
y+0.211
les+0.205
Neg logit contributions
 pleasure-0.202
 Deal-0.179
 welcome-0.158
 learn-0.153
 think-0.151
Token beautiful
Token ID4950
Feature activation-1.57e+00

Pos logit contributions
 pleasure+0.279
 Deal+0.217
 welcome+0.199
 great+0.188
 learn+0.185
Neg logit contributions
led-0.563
ed-0.483
ied-0.438
y-0.430
ted-0.416
Token light
Token ID1657
Feature activation-1.12e+00

Pos logit contributions
 pleasure+0.082
 Deal+0.064
 welcome+0.064
 think+0.060
 great+0.060
Neg logit contributions
led-0.117
ed-0.098
ied-0.088
y-0.083
med-0.082
Token a
Token ID257
Feature activation+9.65e-01

Pos logit contributions
 think+0.114
 great+0.111
 not+0.110
 be+0.110
 have+0.108
Neg logit contributions
led-0.173
ier-0.155
ing-0.150
ed-0.144
ied-0.143
Token shiny
Token ID22441
Feature activation+6.51e+00

Pos logit contributions
led+0.070
ed+0.059
y+0.057
ling+0.054
les+0.053
Neg logit contributions
 pleasure-0.043
 Deal-0.042
 learn-0.033
 know-0.032
 Not-0.032
Token rock
Token ID3881
Feature activation+3.81e+00

Pos logit contributions
led+0.482
ed+0.400
ied+0.356
we+0.344
med+0.342
Neg logit contributions
 pleasure-0.344
 Deal-0.283
 welcome-0.277
 think-0.260
 learn-0.259
Token that
Token ID326
Feature activation+3.44e+00

Pos logit contributions
led+0.270
ed+0.211
ied+0.204
med+0.195
awed+0.192
Neg logit contributions
 pleasure-0.175
 welcome-0.149
 think-0.148
 learn-0.141
 see-0.140
Token spark
Token ID9009
Feature activation+5.76e+00

Pos logit contributions
led+0.229
ed+0.184
ied+0.163
y+0.159
ling+0.158
Neg logit contributions
 pleasure-0.203
 Deal-0.170
 welcome-0.169
 think-0.163
 great-0.160
Tokenled
Token ID992
Feature activation+2.63e+01

Pos logit contributions
led+0.093
awed+0.064
ied+0.062
we+0.049
ainted+0.047
Neg logit contributions
 pleasure-0.474
 great-0.448
 fun-0.432
 think-0.429
 love-0.422
Token in
Token ID287
Feature activation+1.35e+01

Pos logit contributions
led+1.731
ed+1.386
ied+1.254
awed+1.223
les+1.203
Neg logit contributions
 pleasure-1.589
 welcome-1.335
 great-1.294
 OK-1.244
 Deal-1.235
Token the
Token ID262
Feature activation+3.92e+00

Pos logit contributions
led+1.009
ed+0.847
y+0.767
ied+0.756
les+0.733
Neg logit contributions
 pleasure-0.670
 Deal-0.611
 welcome-0.506
 learn-0.498
 OK-0.490
Token sun
Token ID4252
Feature activation-3.59e+00

Pos logit contributions
led+0.313
ed+0.263
ied+0.236
y+0.233
les+0.227
Neg logit contributions
 pleasure-0.184
 Deal-0.158
 welcome-0.141
 learn-0.134
 think-0.132
Token.
Token ID13
Feature activation+6.64e+00

Pos logit contributions
 pleasure+0.203
 welcome+0.165
 learn+0.157
 +0.157
 OK+0.157
Neg logit contributions
led-0.239
ed-0.188
ied-0.174
awed-0.162
ils-0.160
Token She
Token ID1375
Feature activation+4.01e+00

Pos logit contributions
led+0.514
ed+0.461
y+0.415
ied+0.401
ted+0.400
Neg logit contributions
 pleasure-0.268
 Deal-0.234
 learn-0.200
 welcome-0.197
 great-0.195
Token
Token ID198
Feature activation-4.90e+00

Pos logit contributions
 pleasure+0.199
 Deal+0.172
 welcome+0.152
 learn+0.146
 think+0.144
Neg logit contributions
led-0.322
ed-0.270
ied-0.242
y-0.239
les-0.233
Token
Token ID198
Feature activation-5.88e+00

Pos logit contributions
 pleasure+0.242
 Deal+0.186
 deal+0.171
 welcome+0.162
 great+0.158
Neg logit contributions
led-0.358
ed-0.306
y-0.289
ied-0.279
med-0.276
TokenS
Token ID50
Feature activation+7.18e+00

Pos logit contributions
 pleasure+0.351
 Deal+0.286
 welcome+0.259
 deal+0.253
 opinion+0.248
Neg logit contributions
led-0.369
ed-0.307
y-0.289
ied-0.278
we-0.274
Tokenara
Token ID3301
Feature activation+9.68e+00

Pos logit contributions
led+0.532
ed+0.443
ied+0.394
y+0.380
med+0.377
Neg logit contributions
 pleasure-0.370
 Deal-0.334
 welcome-0.299
 learn-0.284
 think-0.282
Token gigg
Token ID30442
Feature activation+8.54e-01

Pos logit contributions
led+0.647
ed+0.518
ied+0.479
y+0.446
we+0.442
Neg logit contributions
 pleasure-0.551
 Deal-0.492
 think-0.458
 welcome-0.455
 learn-0.453
Tokenled
Token ID992
Feature activation+2.63e+01

Pos logit contributions
led+0.001
we-0.001
web-0.002
stones-0.004
ed-0.005
Neg logit contributions
 Deal-0.085
 pleasure-0.083
 OK-0.078
 welcome-0.077
 okay-0.077
Token.
Token ID13
Feature activation+6.90e+00

Pos logit contributions
led+1.723
ed+1.403
y+1.210
ied+1.189
ling+1.160
Neg logit contributions
 pleasure-1.595
 Deal-1.440
 welcome-1.285
 learn-1.261
 know-1.241
Token She
Token ID1375
Feature activation+4.13e+00

Pos logit contributions
led+0.454
ed+0.414
y+0.360
ing+0.342
ted+0.339
Neg logit contributions
 pleasure-0.354
 Deal-0.319
 learn-0.284
 great-0.278
 think-0.276
Token picked
Token ID6497
Feature activation+1.02e+01

Pos logit contributions
led+0.262
ed+0.211
ied+0.186
y+0.181
ing+0.175
Neg logit contributions
 pleasure-0.256
 Deal-0.228
 welcome-0.211
 think-0.208
 learn-0.207
Token up
Token ID510
Feature activation+1.87e+00

Pos logit contributions
led+0.726
ed+0.601
ied+0.528
y+0.523
les+0.508
Neg logit contributions
 pleasure-0.561
 Deal-0.499
 welcome-0.446
 learn-0.431
 think-0.425
Token her
Token ID607
Feature activation+3.49e+00

Pos logit contributions
led+0.157
ed+0.133
ied+0.121
y+0.119
ling+0.117
Neg logit contributions
 pleasure-0.079
 Deal-0.066
 welcome-0.058
 learn-0.056
 think-0.055
Token
Token ID198
Feature activation-6.76e+00

Pos logit contributions
 pleasure+0.279
 Deal+0.203
 deal+0.180
 welcome+0.170
 great+0.168
Neg logit contributions
led-0.492
ed-0.421
y-0.400
ied-0.393
we-0.382
TokenThe
Token ID464
Feature activation+8.50e+00

Pos logit contributions
 pleasure+0.427
 Deal+0.344
 welcome+0.318
 deal+0.305
 great+0.303
Neg logit contributions
led-0.424
ed-0.341
y-0.320
ied-0.309
we-0.306
Token boy
Token ID2933
Feature activation+3.09e+00

Pos logit contributions
led+0.633
ed+0.525
ied+0.467
y+0.466
ling+0.454
Neg logit contributions
 pleasure-0.434
 Deal-0.381
 welcome-0.334
 learn-0.324
 know-0.321
Token sc
Token ID629
Feature activation+2.00e+00

Pos logit contributions
led+0.199
ed+0.161
ied+0.146
y+0.139
we+0.137
Neg logit contributions
 pleasure-0.180
 Deal-0.159
 think-0.152
 learn-0.151
 welcome-0.148
Tokenow
Token ID322
Feature activation+2.98e+00

Pos logit contributions
led+0.121
ed+0.090
y+0.083
ling+0.081
we+0.080
Neg logit contributions
 pleasure-0.132
 Deal-0.120
 welcome-0.112
 know-0.110
 learn-0.109
Tokenled
Token ID992
Feature activation+2.63e+01

Pos logit contributions
led+0.006
stones+0.001
web-0.005
we-0.005
pled-0.006
Neg logit contributions
 welcome-0.262
 know-0.261
 great-0.260
 pleasure-0.260
 thank-0.259
Token and
Token ID290
Feature activation-2.80e+00

Pos logit contributions
led+1.857
ed+1.514
ied+1.362
y+1.314
les+1.294
Neg logit contributions
 pleasure-1.475
 Deal-1.299
 welcome-1.192
 think-1.143
 learn-1.140
Token said
Token ID531
Feature activation+1.81e+00

Pos logit contributions
 pleasure+0.150
 think+0.131
 Deal+0.126
 see+0.124
 welcome+0.123
Neg logit contributions
led-0.185
ed-0.150
ied-0.145
y-0.138
ier-0.137
Token,
Token ID11
Feature activation-4.15e+00

Pos logit contributions
led+0.159
ed+0.129
les+0.124
ied+0.123
y+0.122
Neg logit contributions
 pleasure-0.068
 Deal-0.053
 welcome-0.052
 OK-0.049
 great-0.046
Token "
Token ID366
Feature activation+2.33e-01

Pos logit contributions
 pleasure+0.189
 Deal+0.162
 welcome+0.140
 learn+0.136
 know+0.132
Neg logit contributions
led-0.329
ed-0.285
y-0.253
ied-0.250
ing-0.245
TokenWell
Token ID5779
Feature activation+3.83e+00

Pos logit contributions
led+0.017
ed+0.014
ied+0.013
y+0.013
les+0.012
Neg logit contributions
 pleasure-0.012
 Deal-0.011
 welcome-0.010
 learn-0.009
 think-0.009
Token graceful
Token ID44363
Feature activation+4.87e+00

Pos logit contributions
led+0.220
ed+0.178
y+0.151
ied+0.149
ling+0.148
Neg logit contributions
 pleasure-0.232
 Deal-0.216
 welcome-0.189
 OK-0.189
 know-0.187
Token car
Token ID1097
Feature activation+5.22e+00

Pos logit contributions
led+0.348
ed+0.285
ied+0.257
y+0.243
med+0.242
Neg logit contributions
 pleasure-0.267
 Deal-0.223
 welcome-0.214
 think-0.203
 learn-0.202
Token -
Token ID532
Feature activation+4.05e+00

Pos logit contributions
led+0.353
ed+0.273
ied+0.261
awed+0.246
ling+0.244
Neg logit contributions
 pleasure-0.283
 welcome-0.232
 learn-0.229
 think-0.225
 know-0.217
Token it
Token ID340
Feature activation-2.03e+00

Pos logit contributions
led+0.308
ed+0.263
y+0.237
ied+0.232
ing+0.227
Neg logit contributions
 pleasure-0.186
 Deal-0.173
 welcome-0.139
 learn-0.134
 know-0.130
Token spark
Token ID9009
Feature activation+5.83e+00

Pos logit contributions
 pleasure+0.115
 Deal+0.096
 welcome+0.094
 think+0.094
 learn+0.091
Neg logit contributions
led-0.138
ed-0.112
ied-0.101
awed-0.095
y-0.094
Tokenled
Token ID992
Feature activation+2.62e+01

Pos logit contributions
led+0.075
ied+0.030
ed+0.026
we+0.021
awed+0.013
Neg logit contributions
 pleasure-0.548
 great-0.503
 think-0.483
 welcome-0.477
 fun-0.475
Token in
Token ID287
Feature activation+1.35e+01

Pos logit contributions
led+1.770
ed+1.440
ied+1.284
we+1.220
les+1.219
Neg logit contributions
 pleasure-1.562
 welcome-1.277
 Deal-1.275
 great-1.209
 think-1.181
Token the
Token ID262
Feature activation+3.99e+00

Pos logit contributions
led+0.911
ed+0.757
y+0.696
ied+0.678
med+0.670
Neg logit contributions
 pleasure-0.701
 Deal-0.662
 learn-0.550
 OK-0.547
 Not-0.545
Token sunshine
Token ID34488
Feature activation-6.98e+00

Pos logit contributions
led+0.306
ed+0.255
ied+0.227
y+0.227
les+0.222
Neg logit contributions
 pleasure-0.196
 Deal-0.173
 welcome-0.150
 learn-0.146
 think-0.144
Token.
Token ID13
Feature activation+6.87e+00

Pos logit contributions
 pleasure+0.399
 welcome+0.328
 Deal+0.315
 learn+0.309
 think+0.306
Neg logit contributions
led-0.475
ed-0.378
ied-0.344
awed-0.322
ted-0.314
Token One
Token ID1881
Feature activation-5.86e+00

Pos logit contributions
led+0.547
ed+0.494
y+0.446
med+0.432
ied+0.429
Neg logit contributions
 pleasure-0.256
 Deal-0.221
 learn-0.189
 deal-0.187
 great-0.185
Token looked
Token ID3114
Feature activation+5.59e+00

Pos logit contributions
led+0.116
ed+0.094
ied+0.084
y+0.082
les+0.080
Neg logit contributions
 pleasure-0.094
 Deal-0.082
 welcome-0.076
 think-0.074
 learn-0.074
Token at
Token ID379
Feature activation+1.04e+01

Pos logit contributions
led+0.466
ed+0.390
ied+0.351
y+0.351
ling+0.347
Neg logit contributions
 pleasure-0.239
 Deal-0.214
 welcome-0.174
 learn-0.173
 know-0.166
Token them
Token ID606
Feature activation-1.38e+00

Pos logit contributions
led+0.776
ed+0.655
ied+0.586
y+0.585
les+0.563
Neg logit contributions
 pleasure-0.524
 Deal-0.475
 welcome-0.394
 learn-0.381
 OK-0.377
Token and
Token ID290
Feature activation-1.45e+00

Pos logit contributions
 pleasure+0.084
 Deal+0.075
 welcome+0.070
 learn+0.068
 think+0.068
Neg logit contributions
led-0.089
ed-0.072
ied-0.062
y-0.060
les-0.059
Token grow
Token ID1663
Feature activation-1.51e+00

Pos logit contributions
 pleasure+0.084
 Deal+0.073
 think+0.070
 welcome+0.069
 learn+0.068
Neg logit contributions
led-0.095
ed-0.077
ied-0.071
y-0.067
ing-0.066
Tokenled
Token ID992
Feature activation+2.62e+01

Pos logit contributions
 great+0.134
 pleasure+0.130
 okay+0.129
 welcome+0.128
 OK+0.128
Neg logit contributions
led-0.013
web-0.008
ase-0.006
we-0.006
emaker-0.004
Token again
Token ID757
Feature activation+2.22e+00

Pos logit contributions
led+1.715
ed+1.368
ied+1.235
les+1.151
y+1.150
Neg logit contributions
 pleasure-1.616
 Deal-1.375
 welcome-1.351
 OK-1.308
 think-1.288
Token.
Token ID13
Feature activation+7.08e+00

Pos logit contributions
led+0.136
ed+0.108
ied+0.095
y+0.088
les+0.088
Neg logit contributions
 pleasure-0.144
 Deal-0.127
 welcome-0.121
 learn-0.117
 think-0.117
Token Tom
Token ID4186
Feature activation-1.02e+00

Pos logit contributions
led+0.520
ed+0.476
y+0.418
es+0.403
ted+0.401
Neg logit contributions
 pleasure-0.307
 Deal-0.256
 learn-0.229
 deal-0.226
 great-0.226
Token and
Token ID290
Feature activation-2.67e+00

Pos logit contributions
 pleasure+0.050
 Deal+0.043
 think+0.042
 welcome+0.041
 learn+0.041
Neg logit contributions
led-0.074
ed-0.060
ied-0.057
we-0.054
ier-0.053
Token Lily
Token ID20037
Feature activation+7.51e-01

Pos logit contributions
 pleasure+0.098
 Deal+0.081
 welcome+0.072
 think+0.068
 learn+0.067
Neg logit contributions
led-0.240
ed-0.204
ied-0.189
y-0.183
ling-0.183
Token
Token ID198
Feature activation-6.56e+00

Pos logit contributions
 pleasure+0.457
 Deal+0.347
 deal+0.294
 learn+0.291
 welcome+0.289
Neg logit contributions
led-1.010
ed-0.897
y-0.823
ied-0.808
ing-0.792
Token
Token ID198
Feature activation-7.03e+00

Pos logit contributions
 pleasure+0.255
 Deal+0.191
 welcome+0.155
 deal+0.154
 learn+0.148
Neg logit contributions
led-0.565
ed-0.493
y-0.461
ied-0.448
med-0.447
TokenDad
Token ID46270
Feature activation+2.37e+00

Pos logit contributions
 pleasure+0.418
 Deal+0.353
 welcome+0.320
 learn+0.303
 deal+0.303
Neg logit contributions
led-0.461
ed-0.383
y-0.347
ied-0.336
med-0.333
Token r
Token ID374
Feature activation+6.62e+00

Pos logit contributions
led+0.160
ed+0.126
ied+0.119
we+0.119
web+0.113
Neg logit contributions
 pleasure-0.119
 think-0.106
 Deal-0.106
 welcome-0.101
 know-0.101
Tokenuff
Token ID1648
Feature activation+5.97e+00

Pos logit contributions
led+0.420
ed+0.315
les+0.304
ted+0.299
lers+0.299
Neg logit contributions
 pleasure-0.354
 Deal-0.354
 welcome-0.308
 OK-0.292
 opinion-0.290
Tokenled
Token ID992
Feature activation+2.62e+01

Pos logit contributions
led+0.141
ed+0.081
attered+0.071
awed+0.063
web+0.060
Neg logit contributions
 pleasure-0.452
 think-0.451
 welcome-0.431
 learn-0.427
 Deal-0.426
Token his
Token ID465
Feature activation+3.85e+00

Pos logit contributions
led+2.004
ed+1.651
ied+1.493
les+1.447
y+1.427
Neg logit contributions
 pleasure-1.305
 Deal-1.095
 welcome-1.016
 great-0.966
 think-0.966
Token hair
Token ID4190
Feature activation-4.55e+00

Pos logit contributions
led+0.293
ed+0.244
ied+0.219
y+0.214
les+0.211
Neg logit contributions
 pleasure-0.194
 Deal-0.165
 welcome-0.149
 learn-0.143
 think-0.142
Token and
Token ID290
Feature activation-2.84e+00

Pos logit contributions
 pleasure+0.177
 learn+0.163
 great+0.151
 Deal+0.151
 think+0.150
Neg logit contributions
led-0.333
ed-0.270
ied-0.250
we-0.243
awed-0.242
Token said
Token ID531
Feature activation+1.52e+00

Pos logit contributions
 pleasure+0.155
 Deal+0.134
 think+0.128
 learn+0.126
 welcome+0.124
Neg logit contributions
led-0.196
ed-0.160
ied-0.146
y-0.140
ling-0.138
Token,
Token ID11
Feature activation-4.18e+00

Pos logit contributions
led+0.127
ed+0.106
ied+0.097
y+0.096
les+0.096
Neg logit contributions
 pleasure-0.064
 Deal-0.053
 welcome-0.048
 OK-0.045
 learn-0.045
Token much
Token ID881
Feature activation-6.60e-01

Pos logit contributions
 pleasure+0.399
 Deal+0.341
 welcome+0.313
 learn+0.300
 think+0.298
Neg logit contributions
led-0.579
ed-0.484
ied-0.430
y-0.427
les-0.420
Token that
Token ID326
Feature activation+2.87e+00

Pos logit contributions
 pleasure+0.035
 Deal+0.028
 welcome+0.028
 think+0.026
 great+0.026
Neg logit contributions
led-0.050
ed-0.041
ied-0.037
y-0.036
ling-0.035
Token she
Token ID673
Feature activation+6.42e+00

Pos logit contributions
led+0.205
ed+0.169
ied+0.149
y+0.148
les+0.143
Neg logit contributions
 pleasure-0.158
 Deal-0.140
 welcome-0.126
 learn-0.121
 think-0.120
Token quickly
Token ID2952
Feature activation+3.74e+00

Pos logit contributions
led+0.407
ed+0.330
ied+0.298
ing+0.288
y+0.287
Neg logit contributions
 pleasure-0.384
 Deal-0.329
 think-0.321
 learn-0.317
 know-0.316
Token tid
Token ID29770
Feature activation+3.70e+00

Pos logit contributions
led+0.236
ed+0.186
ied+0.175
we+0.174
ing+0.171
Neg logit contributions
 pleasure-0.221
 learn-0.190
 think-0.189
 know-0.189
 welcome-0.183
Tokenied
Token ID798
Feature activation+2.62e+01

Pos logit contributions
led+0.097
lers+0.068
awed+0.054
ked+0.051
als+0.049
Neg logit contributions
 pleasure-0.292
 welcome-0.269
 Deal-0.262
 learn-0.259
 know-0.257
Token up
Token ID510
Feature activation+2.11e+00

Pos logit contributions
led+1.915
ed+1.569
y+1.417
ied+1.402
awed+1.342
Neg logit contributions
 pleasure-1.343
 Deal-1.106
 learn-1.064
 welcome-1.061
 think-1.041
Token her
Token ID607
Feature activation+3.15e+00

Pos logit contributions
led+0.163
ed+0.136
ied+0.122
y+0.120
ling+0.117
Neg logit contributions
 pleasure-0.102
 Deal-0.084
 welcome-0.080
 learn-0.078
 think-0.076
Token room
Token ID2119
Feature activation-4.41e+00

Pos logit contributions
led+0.231
ed+0.192
ied+0.170
y+0.168
les+0.163
Neg logit contributions
 pleasure-0.167
 Deal-0.146
 welcome-0.132
 learn-0.127
 think-0.126
Token.
Token ID13
Feature activation+6.34e+00

Pos logit contributions
 pleasure+0.239
 Deal+0.195
 welcome+0.192
 learn+0.190
 think+0.186
Neg logit contributions
led-0.310
ed-0.249
ied-0.223
ted-0.218
les-0.218
Token Her
Token ID2332
Feature activation+4.67e+00

Pos logit contributions
led+0.458
ed+0.430
y+0.380
ted+0.368
ied+0.366
Neg logit contributions
 pleasure-0.249
 Deal-0.217
 deal-0.196
 learn-0.195
 plan-0.192
Token Suddenly
Token ID24975
Feature activation-1.99e+00

Pos logit contributions
 pleasure+0.176
 Deal+0.157
 think+0.151
 welcome+0.150
 learn+0.149
Neg logit contributions
led-0.221
ed-0.187
y-0.163
ied-0.162
ing-0.162
Token,
Token ID11
Feature activation-1.61e+00

Pos logit contributions
 pleasure+0.085
 Deal+0.070
 welcome+0.064
 think+0.061
 learn+0.061
Neg logit contributions
led-0.164
ed-0.137
ied-0.127
y-0.124
les-0.122
Token his
Token ID465
Feature activation+5.25e+00

Pos logit contributions
 pleasure+0.079
 Deal+0.068
 welcome+0.061
 learn+0.058
 think+0.058
Neg logit contributions
led-0.124
ed-0.104
ied-0.093
y-0.092
les-0.090
Token mom
Token ID1995
Feature activation-4.54e+00

Pos logit contributions
led+0.461
ed+0.395
ied+0.359
y+0.356
les+0.347
Neg logit contributions
 pleasure-0.200
 Deal-0.168
 welcome-0.142
 learn-0.135
 think-0.132
Token tick
Token ID4378
Feature activation+8.85e+00

Pos logit contributions
 pleasure+0.235
 Deal+0.218
 know+0.206
 learn+0.203
 welcome+0.203
Neg logit contributions
led-0.312
ed-0.244
ied-0.224
we-0.209
les-0.208
Tokenled
Token ID992
Feature activation+2.61e+01

Pos logit contributions
led+0.085
ed+0.018
ied+0.002
we-0.004
web-0.005
Neg logit contributions
 pleasure-0.826
 Deal-0.813
 great-0.779
 practice-0.768
 welcome-0.763
Token him
Token ID683
Feature activation-5.13e-01

Pos logit contributions
led+1.997
ed+1.663
ied+1.494
y+1.454
les+1.435
Neg logit contributions
 pleasure-1.309
 Deal-1.139
 welcome-1.030
 think-0.984
 learn-0.976
Token and
Token ID290
Feature activation-2.42e+00

Pos logit contributions
 pleasure+0.028
 Deal+0.024
 OK+0.024
 welcome+0.023
 think+0.023
Neg logit contributions
led-0.035
ed-0.027
ied-0.025
les-0.024
awed-0.024
Token he
Token ID339
Feature activation+6.58e+00

Pos logit contributions
 pleasure+0.131
 Deal+0.116
 think+0.109
 welcome+0.108
 OK+0.106
Neg logit contributions
led-0.167
ed-0.133
ied-0.126
y-0.118
les-0.118
Token laughed
Token ID13818
Feature activation+7.29e+00

Pos logit contributions
led+0.409
ed+0.321
ied+0.298
y+0.278
ier+0.274
Neg logit contributions
 pleasure-0.393
 Deal-0.348
 think-0.338
 know-0.334
 learn-0.328
Token and
Token ID290
Feature activation-2.88e+00

Pos logit contributions
led+0.518
ed+0.409
ied+0.395
lers+0.370
awed+0.369
Neg logit contributions
 pleasure-0.382
 Deal-0.322
 OK-0.319
 welcome-0.307
 great-0.307
Token.
Token ID13
Feature activation+9.81e+00

Pos logit contributions
led+0.271
ed+0.227
y+0.210
ling+0.209
les+0.207
Neg logit contributions
 pleasure-0.172
 Deal-0.166
 OK-0.133
 learn-0.128
 Not-0.127
Token But
Token ID887
Feature activation-9.28e+00

Pos logit contributions
led+0.778
ed+0.693
y+0.631
ied+0.602
med+0.596
Neg logit contributions
 pleasure-0.402
 Deal-0.335
 welcome-0.279
 great-0.279
 learn-0.278
Token it
Token ID340
Feature activation-1.66e+00

Pos logit contributions
 pleasure+0.461
 Deal+0.408
 welcome+0.351
 learn+0.338
 know+0.330
Neg logit contributions
led-0.705
ed-0.592
y-0.529
ied-0.525
ling-0.503
Token tw
Token ID665
Feature activation+6.82e+00

Pos logit contributions
 pleasure+0.085
 Deal+0.072
 think+0.072
 learn+0.069
 know+0.069
Neg logit contributions
led-0.115
ed-0.096
ied-0.088
med-0.083
we-0.082
Tokenink
Token ID676
Feature activation+1.35e+01

Pos logit contributions
led+0.448
ed+0.357
ied+0.311
y+0.307
les+0.298
Neg logit contributions
 pleasure-0.423
 Deal-0.381
 welcome-0.351
 learn-0.340
 think-0.334
Tokenled
Token ID992
Feature activation+2.61e+01

Pos logit contributions
led+0.395
ed+0.271
ied+0.233
we+0.232
med+0.203
Neg logit contributions
 pleasure-1.113
 welcome-1.014
 great-1.013
 think-1.012
 Deal-1.011
Token in
Token ID287
Feature activation+1.34e+01

Pos logit contributions
led+1.852
ed+1.527
ied+1.356
y+1.313
les+1.297
Neg logit contributions
 pleasure-1.455
 Deal-1.264
 welcome-1.167
 think-1.109
 OK-1.106
Token the
Token ID262
Feature activation+4.16e+00

Pos logit contributions
led+0.901
ed+0.749
y+0.711
ied+0.668
med+0.661
Neg logit contributions
 pleasure-0.690
 Deal-0.639
 learn-0.537
 Not-0.535
 OK-0.517
Token sunlight
Token ID19606
Feature activation+1.43e+00

Pos logit contributions
led+0.321
ed+0.268
ied+0.239
y+0.238
les+0.232
Neg logit contributions
 pleasure-0.204
 Deal-0.178
 welcome-0.156
 learn-0.151
 think-0.149
Token and
Token ID290
Feature activation-2.63e+00

Pos logit contributions
led+0.101
ed+0.080
ied+0.074
lers+0.070
awed+0.069
Neg logit contributions
 pleasure-0.076
 welcome-0.063
 Deal-0.061
 OK-0.059
 learn-0.059
Token danced
Token ID39480
Feature activation+1.03e+01

Pos logit contributions
 pleasure+0.145
 Deal+0.121
 welcome+0.116
 think+0.116
 learn+0.114
Neg logit contributions
led-0.181
ed-0.147
ied-0.135
y-0.132
ling-0.128
Token
Token ID220
Feature activation-1.20e+01

Pos logit contributions
led+0.237
ed+0.209
y+0.190
ted+0.182
ied+0.181
Neg logit contributions
 pleasure-0.110
 Deal-0.086
 great-0.071
 welcome-0.071
 learn-0.068
Token
Token ID198
Feature activation-6.86e+00

Pos logit contributions
 pleasure+0.448
 Deal+0.340
 deal+0.283
 learn+0.282
 welcome+0.279
Neg logit contributions
led-1.075
ed-0.950
y-0.866
ied-0.863
ing-0.838
Token
Token ID198
Feature activation-7.23e+00

Pos logit contributions
 pleasure+0.269
 Deal+0.201
 welcome+0.166
 deal+0.162
 learn+0.157
Neg logit contributions
led-0.594
ed-0.514
y-0.482
ied-0.473
med-0.465
TokenHenry
Token ID32476
Feature activation+6.88e+00

Pos logit contributions
 pleasure+0.435
 Deal+0.364
 welcome+0.334
 deal+0.313
 learn+0.313
Neg logit contributions
led-0.473
ed-0.389
y-0.353
ied-0.346
we-0.340
Token gigg
Token ID30442
Feature activation+8.10e-01

Pos logit contributions
led+0.436
ed+0.351
ied+0.317
we+0.303
ier+0.301
Neg logit contributions
 pleasure-0.408
 Deal-0.357
 think-0.342
 welcome-0.338
 learn-0.336
Tokenled
Token ID992
Feature activation+2.61e+01

Pos logit contributions
we+0.003
web+0.001
led+0.000
stones-0.001
ed-0.002
Neg logit contributions
 pleasure-0.074
 Deal-0.073
 think-0.069
 great-0.068
 opinion-0.068
Token and
Token ID290
Feature activation-2.93e+00

Pos logit contributions
led+1.787
ed+1.463
ied+1.268
y+1.267
ling+1.222
Neg logit contributions
 pleasure-1.514
 Deal-1.359
 welcome-1.216
 learn-1.183
 think-1.163
Token followed
Token ID3940
Feature activation+7.73e+00

Pos logit contributions
 pleasure+0.176
 Deal+0.155
 welcome+0.144
 think+0.140
 learn+0.140
Neg logit contributions
led-0.192
ed-0.155
ied-0.138
y-0.135
les-0.130
Token the
Token ID262
Feature activation+3.30e+00

Pos logit contributions
led+0.613
ed+0.517
ied+0.464
y+0.459
les+0.447
Neg logit contributions
 pleasure-0.363
 Deal-0.316
 welcome-0.275
 learn-0.263
 think-0.258
Token cat
Token ID3797
Feature activation+5.76e+00

Pos logit contributions
led+0.250
ed+0.208
ied+0.185
y+0.183
les+0.177
Neg logit contributions
 pleasure-0.169
 Deal-0.147
 welcome-0.132
 learn-0.127
 think-0.125
Token.
Token ID13
Feature activation+6.18e+00

Pos logit contributions
led+0.404
ed+0.315
ied+0.286
awed+0.275
ier+0.273
Neg logit contributions
 pleasure-0.321
 learn-0.282
 welcome-0.273
 think-0.272
 Deal-0.272
Token,
Token ID11
Feature activation-1.54e+00

Pos logit contributions
 pleasure+0.186
 great+0.156
 think+0.149
 learn+0.148
 know+0.145
Neg logit contributions
led-0.264
ed-0.204
awed-0.202
ling-0.198
les-0.197
Token Bob
Token ID5811
Feature activation+9.29e-01

Pos logit contributions
 pleasure+0.076
 Deal+0.067
 welcome+0.056
 learn+0.055
 know+0.054
Neg logit contributions
led-0.116
ed-0.098
y-0.088
ied-0.086
ling-0.084
Token's
Token ID338
Feature activation+7.36e+00

Pos logit contributions
led+0.060
ed+0.048
ied+0.044
we+0.040
med+0.040
Neg logit contributions
 pleasure-0.055
 Deal-0.048
 welcome-0.047
 think-0.046
 know-0.045
Token eyes
Token ID2951
Feature activation-1.21e+00

Pos logit contributions
led+0.576
ed+0.491
y+0.449
ied+0.447
ling+0.433
Neg logit contributions
 pleasure-0.301
 Deal-0.275
 learn-0.227
 know-0.222
 welcome-0.221
Token spark
Token ID9009
Feature activation+5.75e+00

Pos logit contributions
 pleasure+0.066
 Deal+0.058
 welcome+0.054
 learn+0.054
 think+0.053
Neg logit contributions
led-0.084
ed-0.070
ied-0.063
y-0.060
we-0.059
Tokenled
Token ID992
Feature activation+2.61e+01

Pos logit contributions
led+0.143
ied+0.137
ase+0.136
we+0.129
web+0.126
Neg logit contributions
 pleasure-0.399
 great-0.381
 okay-0.358
 fun-0.357
 OK-0.352
Token with
Token ID351
Feature activation+2.83e+00

Pos logit contributions
led+1.679
ed+1.356
ied+1.240
we+1.185
awed+1.169
Neg logit contributions
 pleasure-1.588
 welcome-1.335
 Deal-1.294
 great-1.276
 OK-1.266
Token joy
Token ID8716
Feature activation-1.40e+01

Pos logit contributions
led+0.249
ed+0.214
ied+0.193
y+0.192
les+0.189
Neg logit contributions
 pleasure-0.102
 Deal-0.093
 learn-0.071
 welcome-0.071
 think-0.069
Token.
Token ID13
Feature activation+6.67e+00

Pos logit contributions
 pleasure+0.693
 welcome+0.541
 OK+0.526
 love+0.524
 great+0.514
Neg logit contributions
led-0.918
ed-0.742
ied-0.704
awed-0.691
web-0.671
Token His
Token ID2399
Feature activation+3.41e+00

Pos logit contributions
led+0.447
ed+0.405
y+0.364
ted+0.352
ied+0.340
Neg logit contributions
 pleasure-0.292
 Deal-0.261
 learn-0.256
 great-0.245
 deal-0.240
Token sister
Token ID6621
Feature activation+5.93e-01

Pos logit contributions
led+0.281
ed+0.240
ied+0.216
y+0.215
lers+0.210
Neg logit contributions
 pleasure-0.131
 Deal-0.127
 welcome-0.102
 learn-0.099
 Not-0.099
Token fancy
Token ID14996
Feature activation+1.21e+00

Pos logit contributions
led+0.070
ed+0.059
y+0.057
ling+0.054
les+0.053
Neg logit contributions
 pleasure-0.043
 Deal-0.042
 learn-0.033
 know-0.032
 Not-0.032
Token crystal
Token ID15121
Feature activation+7.85e+00

Pos logit contributions
led+0.091
ed+0.076
ied+0.067
y+0.066
ling+0.064
Neg logit contributions
 pleasure-0.063
 Deal-0.054
 welcome-0.050
 learn-0.047
 think-0.047
Token necklace
Token ID38987
Feature activation+6.02e+00

Pos logit contributions
led+0.557
ed+0.454
ied+0.429
awed+0.402
med+0.396
Neg logit contributions
 pleasure-0.401
 welcome-0.324
 think-0.314
 great-0.312
 be-0.305
Token that
Token ID326
Feature activation+2.88e+00

Pos logit contributions
led+0.417
ed+0.316
ied+0.312
ling+0.301
awed+0.296
Neg logit contributions
 pleasure-0.306
 welcome-0.256
 name-0.236
 OK-0.236
 learn-0.234
Token spark
Token ID9009
Feature activation+5.44e+00

Pos logit contributions
led+0.201
ed+0.163
ied+0.144
y+0.143
ling+0.141
Neg logit contributions
 pleasure-0.164
 Deal-0.139
 welcome-0.134
 think-0.128
 learn-0.128
Tokenled
Token ID992
Feature activation+2.60e+01

Pos logit contributions
led+0.053
ied+0.028
awed+0.024
ainted+0.022
umbled+0.013
Neg logit contributions
 pleasure-0.476
 great-0.454
 fun-0.439
 think-0.427
 know-0.426
Token in
Token ID287
Feature activation+1.33e+01

Pos logit contributions
led+1.701
ed+1.370
ied+1.230
awed+1.220
les+1.176
Neg logit contributions
 pleasure-1.581
 welcome-1.334
 great-1.299
 OK-1.237
 Deal-1.221
Token the
Token ID262
Feature activation+3.81e+00

Pos logit contributions
led+0.975
ed+0.812
y+0.741
ied+0.728
les+0.704
Neg logit contributions
 pleasure-0.663
 Deal-0.611
 welcome-0.502
 learn-0.498
 OK-0.492
Token sun
Token ID4252
Feature activation-3.69e+00

Pos logit contributions
led+0.302
ed+0.254
ied+0.227
y+0.225
les+0.219
Neg logit contributions
 pleasure-0.180
 Deal-0.156
 welcome-0.137
 learn-0.131
 think-0.130
Token.
Token ID13
Feature activation+6.56e+00

Pos logit contributions
 pleasure+0.210
 welcome+0.172
 learn+0.162
 OK+0.162
 +0.162
Neg logit contributions
led-0.245
ed-0.194
ied-0.178
awed-0.167
ted-0.162
Token One
Token ID1881
Feature activation-5.98e+00

Pos logit contributions
led+0.500
ed+0.449
y+0.406
ted+0.391
med+0.390
Neg logit contributions
 pleasure-0.264
 Deal-0.233
 learn-0.199
 great-0.196
 welcome-0.195
Token the
Token ID262
Feature activation+5.73e+00

Pos logit contributions
led+0.626
ed+0.522
y+0.489
ied+0.485
ling+0.469
Neg logit contributions
 pleasure-0.341
 Deal-0.302
 Today-0.230
 Not-0.220
 OK-0.219
Token wind
Token ID2344
Feature activation-6.10e-01

Pos logit contributions
led+0.434
ed+0.363
y+0.327
ied+0.325
ling+0.317
Neg logit contributions
 pleasure-0.279
 Deal-0.247
 welcome-0.210
 know-0.206
 learn-0.204
Token as
Token ID355
Feature activation-4.14e+00

Pos logit contributions
 pleasure+0.033
 Deal+0.029
 welcome+0.027
 think+0.027
 learn+0.027
Neg logit contributions
led-0.043
ed-0.035
ied-0.031
ted-0.029
med-0.029
Token it
Token ID340
Feature activation-2.44e+00

Pos logit contributions
 pleasure+0.181
 Deal+0.143
 welcome+0.141
 great+0.131
 think+0.130
Neg logit contributions
led-0.338
ed-0.290
ied-0.258
les-0.256
y-0.254
Token rust
Token ID17000
Feature activation+9.99e+00

Pos logit contributions
 pleasure+0.147
 Deal+0.129
 think+0.125
 learn+0.124
 welcome+0.123
Neg logit contributions
led-0.149
ed-0.118
ied-0.109
y-0.101
we-0.099
Tokenled
Token ID992
Feature activation+2.60e+01

Pos logit contributions
led+0.167
we+0.108
ed+0.093
ied+0.093
web+0.081
Neg logit contributions
 great-0.831
 pleasure-0.827
 welcome-0.787
 OK-0.771
 okay-0.768
Token through
Token ID832
Feature activation+1.07e+01

Pos logit contributions
led+1.851
ed+1.517
ied+1.381
y+1.304
we+1.300
Neg logit contributions
 pleasure-1.437
 Deal-1.234
 welcome-1.171
 great-1.108
 think-1.105
Token the
Token ID262
Feature activation+3.81e+00

Pos logit contributions
led+0.899
ed+0.760
ied+0.690
y+0.676
les+0.661
Neg logit contributions
 pleasure-0.464
 Deal-0.384
 welcome-0.346
 learn-0.326
 think-0.322
Token leaves
Token ID5667
Feature activation+1.15e+00

Pos logit contributions
led+0.291
ed+0.243
ied+0.218
y+0.212
les+0.205
Neg logit contributions
 pleasure-0.192
 Deal-0.165
 welcome-0.151
 learn-0.144
 think-0.142
Token.
Token ID13
Feature activation+6.41e+00

Pos logit contributions
led+0.080
ed+0.066
ied+0.059
awed+0.057
we+0.057
Neg logit contributions
 pleasure-0.056
 welcome-0.048
 learn-0.046
 think-0.046
 -0.045
Token
Token ID198
Feature activation-8.39e+00

Pos logit contributions
led+0.499
ed+0.456
y+0.404
med+0.395
ted+0.393
Neg logit contributions
 pleasure-0.241
 Deal-0.208
 learn-0.184
 deal-0.179
 welcome-0.177
Token The
Token ID383
Feature activation+7.62e+00

Pos logit contributions
led+0.246
ed+0.206
y+0.180
ied+0.180
les+0.178
Neg logit contributions
 pleasure-0.186
 Deal-0.156
 welcome-0.154
 OK-0.149
 great-0.143
Token cater
Token ID20825
Feature activation+1.04e+01

Pos logit contributions
led+0.548
ed+0.453
y+0.408
ied+0.400
ling+0.397
Neg logit contributions
 pleasure-0.395
 Deal-0.351
 welcome-0.301
 know-0.296
 learn-0.294
Tokenpillar
Token ID41643
Feature activation+1.52e+01

Pos logit contributions
led+0.552
ed+0.415
ied+0.378
we+0.332
med+0.329
Neg logit contributions
 pleasure-0.711
 Deal-0.650
 welcome-0.625
 think-0.608
 know-0.604
Token w
Token ID266
Feature activation+7.09e-01

Pos logit contributions
led+0.990
ed+0.806
ied+0.727
y+0.685
ing+0.674
Neg logit contributions
 pleasure-0.882
 Deal-0.777
 think-0.741
 welcome-0.733
 learn-0.733
Tokenigg
Token ID6950
Feature activation+9.17e+00

Pos logit contributions
led+0.046
ed+0.037
y+0.032
ied+0.032
med+0.031
Neg logit contributions
 pleasure-0.043
 Deal-0.039
 welcome-0.036
 learn-0.034
 know-0.034
Tokenled
Token ID992
Feature activation+2.60e+01

Pos logit contributions
led+0.065
we+0.038
med+0.023
web+0.019
ed-0.009
Neg logit contributions
 pleasure-0.848
 think-0.802
 know-0.790
 welcome-0.789
 great-0.783
Token inside
Token ID2641
Feature activation+9.53e+00

Pos logit contributions
led+1.928
ed+1.599
ied+1.421
y+1.405
les+1.364
Neg logit contributions
 pleasure-1.364
 Deal-1.197
 welcome-1.072
 learn-1.031
 think-1.019
Token and
Token ID290
Feature activation-2.90e+00

Pos logit contributions
led+0.703
ed+0.581
ied+0.513
y+0.504
les+0.494
Neg logit contributions
 pleasure-0.505
 Deal-0.438
 welcome-0.405
 learn-0.387
 think-0.384
Token felt
Token ID2936
Feature activation+2.74e+00

Pos logit contributions
 pleasure+0.168
 think+0.142
 welcome+0.140
 Deal+0.139
 learn+0.139
Neg logit contributions
led-0.184
ed-0.146
ied-0.137
y-0.134
ier-0.131
Token safe
Token ID3338
Feature activation-3.95e+00

Pos logit contributions
led+0.239
ed+0.203
ied+0.181
ling+0.179
y+0.178
Neg logit contributions
 pleasure-0.107
 Deal-0.095
 welcome-0.073
 learn-0.072
 Today-0.071
Token.
Token ID13
Feature activation+6.33e+00

Pos logit contributions
 pleasure+0.204
 welcome+0.170
 OK+0.162
 okay+0.156
 think+0.155
Neg logit contributions
led-0.273
ed-0.213
ied-0.210
les-0.203
med-0.200
Tokenled
Token ID992
Feature activation+2.76e+01

Pos logit contributions
led+0.037
ed+0.014
ied+0.004
web-0.000
we-0.001
Neg logit contributions
 pleasure-0.223
 Deal-0.210
 welcome-0.201
 think-0.198
 OK-0.198
Token as
Token ID355
Feature activation-4.54e+00

Pos logit contributions
led+2.002
ed+1.653
ied+1.501
y+1.447
we+1.447
Neg logit contributions
 pleasure-1.459
 Deal-1.214
 welcome-1.169
 think-1.105
 learn-1.092
Token the
Token ID262
Feature activation+4.86e+00

Pos logit contributions
 pleasure+0.221
 welcome+0.177
 Deal+0.175
 great+0.168
 OK+0.163
Neg logit contributions
led-0.346
ed-0.289
y-0.259
ied-0.258
les-0.256
Token popcorn
Token ID38914
Feature activation+3.67e+00

Pos logit contributions
led+0.368
ed+0.307
ied+0.273
y+0.270
les+0.261
Neg logit contributions
 pleasure-0.248
 Deal-0.215
 welcome-0.194
 learn-0.185
 think-0.183
Token tick
Token ID4378
Feature activation+8.39e+00

Pos logit contributions
led+0.244
ed+0.197
ied+0.184
awed+0.171
med+0.171
Neg logit contributions
 pleasure-0.197
 welcome-0.161
 think-0.157
 learn-0.156
 great-0.155
Tokenled
Token ID992
Feature activation+2.60e+01

Pos logit contributions
led+0.122
ed+0.033
ied+0.022
web+0.002
ier-0.005
Neg logit contributions
 pleasure-0.822
 Deal-0.756
 great-0.747
 welcome-0.730
 think-0.726
Token her
Token ID607
Feature activation+3.51e+00

Pos logit contributions
led+1.927
ed+1.592
ied+1.432
y+1.398
les+1.365
Neg logit contributions
 pleasure-1.355
 Deal-1.155
 welcome-1.067
 learn-1.019
 think-1.018
Token.
Token ID13
Feature activation+6.67e+00

Pos logit contributions
led+0.263
ed+0.218
ied+0.194
y+0.192
les+0.186
Neg logit contributions
 pleasure-0.182
 Deal-0.160
 welcome-0.142
 learn-0.137
 think-0.135
Token
Token ID198
Feature activation-8.24e+00

Pos logit contributions
led+0.557
ed+0.502
y+0.449
ied+0.439
ted+0.436
Neg logit contributions
 pleasure-0.245
 Deal-0.205
 learn-0.174
 welcome-0.171
 think-0.167
Token
Token ID198
Feature activation-8.21e+00

Pos logit contributions
 pleasure+0.330
 Deal+0.258
 deal+0.213
 welcome+0.207
 learn+0.196
Neg logit contributions
led-0.691
ed-0.609
ied-0.565
y-0.563
med-0.544
TokenAm
Token ID5840
Feature activation+1.01e+01

Pos logit contributions
 pleasure+0.460
 Deal+0.385
 welcome+0.347
 deal+0.328
 think+0.326
Neg logit contributions
led-0.569
ed-0.477
ied-0.432
y-0.431
med-0.418
Token -
Token ID532
Feature activation+1.12e+00

Pos logit contributions
 pleasure+0.221
 Deal+0.178
 learn+0.177
 welcome+0.174
 Not+0.170
Neg logit contributions
led-0.332
ed-0.273
ied-0.239
y-0.237
ling-0.236
Token to
Token ID284
Feature activation+3.63e+00

Pos logit contributions
led+0.077
ed+0.065
y+0.059
ied+0.059
ing+0.058
Neg logit contributions
 pleasure-0.059
 Deal-0.056
 welcome-0.047
 OK-0.044
 think-0.043
Token always
Token ID1464
Feature activation-2.75e+00

Pos logit contributions
led+0.219
y+0.193
ied+0.177
ed+0.174
ling+0.174
Neg logit contributions
 pleasure-0.174
 Deal-0.166
 Today-0.133
 OK-0.130
 Okay-0.127
Token share
Token ID2648
Feature activation-4.87e+00

Pos logit contributions
 pleasure+0.098
 Deal+0.087
 Today+0.063
 OK+0.059
 Not+0.058
Neg logit contributions
led-0.223
ed-0.194
y-0.188
ling-0.173
ied-0.171
Token and
Token ID290
Feature activation-4.01e+00

Pos logit contributions
 pleasure+0.293
 Deal+0.274
 Today+0.232
 welcome+0.226
 Not+0.220
Neg logit contributions
led-0.322
ed-0.258
y-0.232
ling-0.224
es-0.223
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
 pleasure+0.148
 Deal+0.146
 Today+0.107
 OK+0.096
 welcome+0.096
Neg logit contributions
led-0.332
ed-0.290
y-0.264
ied-0.262
we-0.255
Token of
Token ID286
Feature activation+1.30e+01

Pos logit contributions
 pleasure+1.393
 Deal+1.178
 welcome+1.130
 great+1.089
 learn+1.085
Neg logit contributions
led-1.652
ed-1.346
y-1.166
ied-1.142
awed-1.131
Token others
Token ID1854
Feature activation-2.84e+00

Pos logit contributions
led+0.833
ed+0.678
we+0.657
es+0.648
ing+0.643
Neg logit contributions
 Deal-0.619
 pleasure-0.610
 Today-0.562
 meantime-0.481
 Once-0.464
Token!
Token ID0
Feature activation+2.26e+00

Pos logit contributions
 pleasure+0.164
 Deal+0.142
 welcome+0.135
 learn+0.132
 think+0.130
Neg logit contributions
led-0.192
ed-0.155
ied-0.139
y-0.131
les-0.131
Token<|endoftext|>
Token ID50256
Feature activation-1.49e+00

Pos logit contributions
led+0.158
ed+0.147
y+0.138
es+0.134
ing+0.130
Neg logit contributions
 pleasure-0.093
 Deal-0.089
 deal-0.074
 welcome-0.071
 plan-0.069
TokenOnce
Token ID7454
Feature activation-7.08e+00

Pos logit contributions
 pleasure+0.045
 Deal+0.036
 welcome+0.029
 learn+0.026
 think+0.026
Neg logit contributions
led-0.142
ed-0.123
ied-0.114
y-0.112
ling-0.110
Token looked
Token ID3114
Feature activation+1.74e+00

Pos logit contributions
led+0.147
ed+0.120
ier+0.117
we+0.114
ing+0.114
Neg logit contributions
 pleasure-0.104
 think-0.100
 great-0.098
 know-0.097
 learn-0.095
Token around
Token ID1088
Feature activation+8.26e+00

Pos logit contributions
led+0.104
ed+0.084
ied+0.071
we+0.070
y+0.070
Neg logit contributions
 pleasure-0.113
 Deal-0.100
 welcome-0.095
 think-0.092
 learn-0.092
Token and
Token ID290
Feature activation-4.17e+00

Pos logit contributions
led+0.536
ed+0.434
y+0.384
ied+0.380
ling+0.363
Neg logit contributions
 pleasure-0.510
 Deal-0.465
 welcome-0.404
 OK-0.398
 know-0.393
Token tried
Token ID3088
Feature activation+7.18e-01

Pos logit contributions
 pleasure+0.260
 Deal+0.231
 welcome+0.214
 think+0.210
 learn+0.210
Neg logit contributions
led-0.267
ed-0.213
ied-0.187
y-0.182
les-0.178
Token to
Token ID284
Feature activation+3.73e+00

Pos logit contributions
led+0.043
ed+0.035
ied+0.031
y+0.031
ing+0.030
Neg logit contributions
 pleasure-0.047
 Deal-0.044
 welcome-0.039
 OK-0.036
 know-0.036
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
led+0.261
ed+0.211
ling+0.200
y+0.199
ied+0.195
Neg logit contributions
 pleasure-0.192
 Deal-0.160
 Today-0.135
 Not-0.132
 Okay-0.127
Token of
Token ID286
Feature activation+1.31e+01

Pos logit contributions
 pleasure+1.407
 Deal+1.224
 welcome+1.151
 learn+1.121
 OK+1.112
Neg logit contributions
led-1.634
ed-1.317
y-1.148
ied-1.117
ling-1.105
Token something
Token ID1223
Feature activation-1.16e+01

Pos logit contributions
led+0.871
ed+0.724
ied+0.671
ing+0.649
we+0.649
Neg logit contributions
 Deal-0.622
 pleasure-0.600
 Today-0.500
 welcome-0.485
 learn-0.451
Token.
Token ID13
Feature activation+5.47e+00

Pos logit contributions
 pleasure+0.575
 Deal+0.457
 welcome+0.456
 great+0.443
 think+0.431
Neg logit contributions
led-0.909
ed-0.757
ied-0.669
y-0.662
med-0.655
Token Suddenly
Token ID24975
Feature activation-6.57e+00

Pos logit contributions
led+0.347
ed+0.342
y+0.283
ing+0.272
ted+0.271
Neg logit contributions
 pleasure-0.281
 Deal-0.262
 welcome-0.227
 deal-0.222
 great-0.217
Token she
Token ID673
Feature activation+3.93e+00

Pos logit contributions
 pleasure+0.250
 Deal+0.196
 welcome+0.183
 learn+0.174
 great+0.173
Neg logit contributions
led-0.573
ed-0.479
ied-0.447
y-0.440
ling-0.437
Token disagreed
Token ID27884
Feature activation-1.34e+00

Pos logit contributions
 pleasure+0.004
 Deal+0.004
 welcome+0.003
 learn+0.003
 think+0.003
Neg logit contributions
led-0.005
ed-0.004
ied-0.004
y-0.004
ling-0.004
Token,
Token ID11
Feature activation-5.18e+00

Pos logit contributions
 pleasure+0.068
 Deal+0.058
 welcome+0.054
 learn+0.052
 think+0.051
Neg logit contributions
led-0.101
ed-0.083
ied-0.074
y-0.072
les-0.071
Token they
Token ID484
Feature activation+2.02e+00

Pos logit contributions
 pleasure+0.262
 Deal+0.235
 welcome+0.204
 learn+0.195
 think+0.192
Neg logit contributions
led-0.391
ed-0.326
ied-0.290
y-0.287
les-0.278
Token tried
Token ID3088
Feature activation+7.71e-01

Pos logit contributions
led+0.136
ed+0.111
we+0.099
awed+0.098
ied+0.097
Neg logit contributions
 pleasure-0.115
 think-0.098
 know-0.098
 learn-0.097
 Deal-0.096
Token to
Token ID284
Feature activation+3.74e+00

Pos logit contributions
led+0.048
ed+0.039
y+0.035
ied+0.035
ing+0.034
Neg logit contributions
 pleasure-0.047
 Deal-0.045
 welcome-0.039
 Today-0.036
 OK-0.036
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
led+0.288
ed+0.241
y+0.237
ling+0.234
les+0.221
Neg logit contributions
 pleasure-0.148
 Deal-0.137
 Today-0.109
 Not-0.101
 Sometimes-0.097
Token of
Token ID286
Feature activation+1.31e+01

Pos logit contributions
 pleasure+1.460
 Deal+1.256
 welcome+1.196
 learn+1.157
 great+1.141
Neg logit contributions
led-1.595
ed-1.285
y-1.112
ied-1.098
ling-1.066
Token solutions
Token ID8136
Feature activation+1.66e+00

Pos logit contributions
led+0.930
ed+0.770
ied+0.694
y+0.693
ing+0.688
Neg logit contributions
 Deal-0.595
 pleasure-0.552
 Today-0.484
 welcome-0.437
 learn-0.429
Token.
Token ID13
Feature activation+5.57e+00

Pos logit contributions
led+0.117
ed+0.094
ied+0.083
awed+0.082
les+0.081
Neg logit contributions
 pleasure-0.092
 Deal-0.076
 welcome-0.075
 think-0.073
 learn-0.073
Token That
Token ID1320
Feature activation-2.48e+00

Pos logit contributions
led+0.419
ed+0.392
y+0.346
med+0.339
es+0.337
Neg logit contributions
 pleasure-0.196
 Deal-0.187
 deal-0.168
 plan-0.156
 great-0.151
Token way
Token ID835
Feature activation-1.04e+01

Pos logit contributions
 pleasure+0.125
 Deal+0.110
 welcome+0.097
 learn+0.093
 think+0.092
Neg logit contributions
led-0.190
ed-0.159
ied-0.142
y-0.140
les-0.136
Token surprised
Token ID6655
Feature activation+2.11e+00

Pos logit contributions
led+0.211
ed+0.181
ied+0.161
y+0.160
med+0.157
Neg logit contributions
 pleasure-0.110
 Deal-0.097
 welcome-0.079
 learn-0.076
 think-0.075
Token since
Token ID1201
Feature activation+1.48e+00

Pos logit contributions
led+0.156
ed+0.128
ied+0.113
y+0.109
les+0.109
Neg logit contributions
 pleasure-0.113
 Deal-0.096
 welcome-0.090
 think-0.086
 learn-0.086
Token he
Token ID339
Feature activation+4.86e+00

Pos logit contributions
led+0.114
ed+0.095
ied+0.085
y+0.084
les+0.082
Neg logit contributions
 pleasure-0.074
 Deal-0.062
 welcome-0.057
 learn-0.055
 think-0.055
Token didn
Token ID1422
Feature activation-3.99e+00

Pos logit contributions
led+0.313
ed+0.250
ied+0.225
y+0.219
les+0.209
Neg logit contributions
 pleasure-0.298
 Deal-0.265
 welcome-0.246
 learn-0.243
 think-0.243
Token't
Token ID470
Feature activation-3.55e+00

Pos logit contributions
 pleasure+0.170
 Deal+0.133
 welcome+0.114
 think+0.102
 deal+0.100
Neg logit contributions
led-0.330
ed-0.292
ied-0.262
y-0.260
ing-0.259
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
 pleasure+0.119
 Deal+0.099
 welcome+0.069
 Today+0.065
 OK+0.064
Neg logit contributions
led-0.324
ed-0.285
y-0.261
ied-0.256
les-0.253
Token his
Token ID465
Feature activation+2.33e+00

Pos logit contributions
 pleasure+1.339
 Deal+1.177
 welcome+1.070
 learn+1.032
 think+1.020
Neg logit contributions
led-1.718
ed-1.413
ied-1.242
y-1.234
les-1.189
Token family
Token ID1641
Feature activation-6.30e+00

Pos logit contributions
led+0.185
ed+0.161
y+0.147
ied+0.144
lers+0.143
Neg logit contributions
 pleasure-0.087
 Deal-0.085
 welcome-0.069
 Not-0.064
 OK-0.063
Token could
Token ID714
Feature activation+1.04e+01

Pos logit contributions
 pleasure+0.357
 Deal+0.294
 welcome+0.294
 learn+0.290
 think+0.289
Neg logit contributions
led-0.434
ed-0.350
ied-0.307
les-0.298
y-0.295
Token be
Token ID307
Feature activation-1.38e+01

Pos logit contributions
led+0.839
ed+0.739
y+0.690
ier+0.661
ling+0.659
Neg logit contributions
 pleasure-0.406
 Deal-0.335
 welcome-0.244
 Today-0.232
 Not-0.225
Token competitive
Token ID7606
Feature activation-9.44e-01

Pos logit contributions
 pleasure+0.708
 welcome+0.586
 Deal+0.572
 OK+0.565
 great+0.565
Neg logit contributions
led-1.018
ed-0.840
ied-0.779
ted-0.748
we-0.738
Token her
Token ID607
Feature activation+2.20e+00

Pos logit contributions
led+1.608
ed+1.322
ied+1.235
we+1.219
les+1.207
Neg logit contributions
 pleasure-0.751
 Deal-0.582
 welcome-0.577
 great-0.543
 OK-0.539
Token chin
Token ID22531
Feature activation-1.15e+00

Pos logit contributions
led+0.172
ed+0.143
ied+0.132
y+0.127
les+0.125
Neg logit contributions
 pleasure-0.108
 Deal-0.092
 welcome-0.082
 think-0.078
 learn-0.077
Token.
Token ID13
Feature activation+5.66e+00

Pos logit contributions
 pleasure+0.054
 OK+0.045
 +0.044
 okay+0.044
 Deal+0.043
Neg logit contributions
led-0.083
ied-0.065
ed-0.065
ils-0.063
we-0.062
Token "
Token ID366
Feature activation-8.45e-01

Pos logit contributions
led+0.418
ed+0.383
y+0.334
ing+0.325
med+0.323
Neg logit contributions
 pleasure-0.247
 Deal-0.214
 learn-0.199
 deal-0.191
 know-0.182
TokenI
Token ID40
Feature activation+8.07e+00

Pos logit contributions
 pleasure+0.044
 Deal+0.039
 welcome+0.035
 learn+0.033
 OK+0.032
Neg logit contributions
led-0.063
ed-0.052
y-0.047
ied-0.046
we-0.045
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
led+0.683
ed+0.589
y+0.536
ied+0.516
les+0.516
Neg logit contributions
 pleasure-0.324
 Deal-0.291
 welcome-0.228
 OK-0.213
 learn-0.208
Token the
Token ID262
Feature activation+2.40e+00

Pos logit contributions
 pleasure+1.076
 Deal+0.933
 welcome+0.803
 learn+0.771
 think+0.756
Neg logit contributions
led-1.975
ed-1.672
ied-1.506
y-1.492
les-1.453
Token gorilla
Token ID45314
Feature activation+7.86e+00

Pos logit contributions
led+0.156
ed+0.130
y+0.112
lers+0.107
les+0.107
Neg logit contributions
 pleasure-0.132
 Deal-0.131
 learn-0.107
 Not-0.105
 OK-0.105
Token must
Token ID1276
Feature activation+1.78e+00

Pos logit contributions
led+0.610
ed+0.510
ied+0.469
med+0.447
we+0.446
Neg logit contributions
 pleasure-0.374
 Deal-0.306
 welcome-0.296
 think-0.287
 know-0.283
Token be
Token ID307
Feature activation-1.39e+01

Pos logit contributions
led+0.158
ed+0.136
y+0.125
ied+0.125
les+0.123
Neg logit contributions
 pleasure-0.062
 Deal-0.053
 Okay-0.035
 OK-0.035
 Not-0.034
Token rich
Token ID5527
Feature activation+5.65e-01

Pos logit contributions
 pleasure+0.646
 Deal+0.536
 welcome+0.503
 think+0.469
 OK+0.467
Neg logit contributions
led-1.109
ed-0.939
ied-0.847
y-0.832
les-0.818
Token his
Token ID465
Feature activation+2.57e+00

Pos logit contributions
led+0.525
ed+0.434
ied+0.394
y+0.385
les+0.382
Neg logit contributions
 pleasure-0.388
 Deal-0.357
 welcome-0.308
 learn-0.302
 OK-0.298
Token bicycle
Token ID17026
Feature activation-2.88e+00

Pos logit contributions
led+0.202
ed+0.172
ied+0.152
y+0.151
ling+0.149
Neg logit contributions
 pleasure-0.114
 Deal-0.103
 welcome-0.089
 know-0.085
 Not-0.085
Token and
Token ID290
Feature activation-3.90e+00

Pos logit contributions
 pleasure+0.123
 learn+0.100
 Deal+0.098
 think+0.096
 great+0.092
Neg logit contributions
led-0.229
ed-0.188
ied-0.176
les-0.164
we-0.163
Token tried
Token ID3088
Feature activation+7.30e-01

Pos logit contributions
 pleasure+0.230
 Deal+0.198
 think+0.187
 learn+0.184
 welcome+0.184
Neg logit contributions
led-0.257
ed-0.206
ied-0.187
y-0.181
les-0.176
Token to
Token ID284
Feature activation+3.78e+00

Pos logit contributions
led+0.040
ed+0.034
y+0.028
ied+0.028
ing+0.028
Neg logit contributions
 pleasure-0.050
 Deal-0.047
 welcome-0.041
 know-0.038
 Not-0.038
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
led+0.271
ed+0.227
ling+0.208
y+0.207
les+0.202
Neg logit contributions
 pleasure-0.188
 Deal-0.164
 Not-0.137
 Today-0.137
 welcome-0.129
Token of
Token ID286
Feature activation+1.30e+01

Pos logit contributions
 pleasure+1.366
 Deal+1.184
 welcome+1.102
 OK+1.062
 learn+1.061
Neg logit contributions
led-1.683
ed-1.362
y-1.200
ied-1.181
ling-1.150
Token ways
Token ID2842
Feature activation-7.71e+00

Pos logit contributions
led+0.897
ed+0.753
ied+0.685
ing+0.666
les+0.662
Neg logit contributions
 Deal-0.603
 pleasure-0.602
 welcome-0.493
 Today-0.487
 learn-0.474
Token to
Token ID284
Feature activation+3.78e+00

Pos logit contributions
 pleasure+0.435
 Deal+0.365
 welcome+0.353
 OK+0.338
 learn+0.337
Neg logit contributions
led-0.551
ed-0.433
ied-0.381
les-0.377
y-0.377
Token get
Token ID651
Feature activation-1.06e+01

Pos logit contributions
led+0.301
ed+0.253
ied+0.232
y+0.231
les+0.229
Neg logit contributions
 pleasure-0.167
 Deal-0.149
 Today-0.116
 welcome-0.115
 Not-0.113
Token better
Token ID1365
Feature activation-4.81e+00

Pos logit contributions
 pleasure+0.517
 Deal+0.427
 welcome+0.407
 learn+0.389
 think+0.387
Neg logit contributions
led-0.822
ed-0.676
y-0.613
ied-0.610
les-0.593
Token,
Token ID11
Feature activation-5.24e+00

Pos logit contributions
 pleasure+0.204
 Deal+0.177
 welcome+0.160
 learn+0.155
 think+0.153
Neg logit contributions
led-0.284
ed-0.235
y-0.207
ied-0.207
les-0.199
Token but
Token ID475
Feature activation-1.20e+01

Pos logit contributions
 pleasure+0.252
 Deal+0.222
 welcome+0.194
 learn+0.180
 know+0.179
Neg logit contributions
led-0.409
ed-0.350
ied-0.306
y-0.306
ing-0.301
Token he
Token ID339
Feature activation+5.04e+00

Pos logit contributions
 pleasure+0.665
 Deal+0.586
 welcome+0.530
 learn+0.514
 think+0.508
Neg logit contributions
led-0.852
ed-0.698
ied-0.616
y-0.609
les-0.595
Token couldn
Token ID3521
Feature activation+2.72e+00

Pos logit contributions
led+0.364
ed+0.293
les+0.268
ied+0.267
we+0.262
Neg logit contributions
 pleasure-0.256
 Deal-0.215
 think-0.213
 know-0.208
 learn-0.204
Token't
Token ID470
Feature activation-3.41e+00

Pos logit contributions
led+0.225
ed+0.199
y+0.177
ied+0.176
ing+0.174
Neg logit contributions
 pleasure-0.116
 Deal-0.091
 welcome-0.078
 think-0.072
 know-0.070
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
 pleasure+0.126
 Deal+0.106
 welcome+0.081
 Not+0.073
 OK+0.072
Neg logit contributions
led-0.295
ed-0.256
y-0.238
ling-0.230
ied-0.229
Token of
Token ID286
Feature activation+1.32e+01

Pos logit contributions
 pleasure+1.412
 Deal+1.193
 welcome+1.148
 great+1.127
 learn+1.123
Neg logit contributions
led-1.643
ed-1.331
y-1.143
awed-1.118
ied-1.108
Token anything
Token ID1997
Feature activation-5.48e+00

Pos logit contributions
led+0.937
ed+0.783
ied+0.703
y+0.702
lers+0.687
Neg logit contributions
 pleasure-0.600
 Deal-0.599
 Today-0.487
 welcome-0.478
 learn-0.463
Token special
Token ID2041
Feature activation-4.24e+00

Pos logit contributions
 pleasure+0.296
 great+0.246
 welcome+0.244
 Deal+0.238
 OK+0.237
Neg logit contributions
led-0.389
ed-0.319
ied-0.286
les-0.274
ted-0.273
Token to
Token ID284
Feature activation+3.86e+00

Pos logit contributions
 pleasure+0.238
 welcome+0.197
 think+0.193
 learn+0.185
 great+0.181
Neg logit contributions
led-0.288
ed-0.225
ied-0.208
awed-0.204
ling-0.204
Token give
Token ID1577
Feature activation-6.39e+00

Pos logit contributions
led+0.322
ed+0.267
y+0.255
ied+0.252
ling+0.246
Neg logit contributions
 pleasure-0.155
 Deal-0.138
 Okay-0.096
 Not-0.096
 OK-0.095
Token bored
Token ID17533
Feature activation+6.94e-01

Pos logit contributions
 pleasure+0.509
 Deal+0.472
 welcome+0.381
 deal+0.377
 learn+0.376
Neg logit contributions
led-0.854
ed-0.718
ied-0.637
y-0.618
ling-0.602
Token.
Token ID13
Feature activation+5.48e+00

Pos logit contributions
led+0.056
ed+0.046
awed+0.042
ied+0.041
lers+0.041
Neg logit contributions
 pleasure-0.027
 fun-0.022
 welcome-0.021
 But-0.021
 see-0.020
Token He
Token ID679
Feature activation+2.32e+00

Pos logit contributions
led+0.366
ed+0.322
y+0.291
ied+0.275
ing+0.263
Neg logit contributions
 pleasure-0.288
 Deal-0.264
 learn-0.224
 welcome-0.223
 great-0.222
Token couldn
Token ID3521
Feature activation+2.73e+00

Pos logit contributions
led+0.148
ed+0.119
ied+0.107
ing+0.103
ier+0.103
Neg logit contributions
 pleasure-0.137
 think-0.120
 Deal-0.119
 learn-0.118
 know-0.117
Token't
Token ID470
Feature activation-3.56e+00

Pos logit contributions
led+0.243
ed+0.214
ied+0.192
y+0.191
les+0.186
Neg logit contributions
 pleasure-0.104
 Deal-0.083
 welcome-0.068
 think-0.061
 OK-0.061
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
 pleasure+0.123
 Deal+0.103
 welcome+0.074
 OK+0.068
 Not+0.065
Neg logit contributions
led-0.322
ed-0.283
y-0.260
ied-0.253
ling-0.250
Token of
Token ID286
Feature activation+1.31e+01

Pos logit contributions
 pleasure+1.411
 Deal+1.225
 welcome+1.153
 learn+1.132
 think+1.111
Neg logit contributions
led-1.629
ed-1.327
y-1.150
ied-1.133
ling-1.096
Token anything
Token ID1997
Feature activation-5.47e+00

Pos logit contributions
led+0.850
ed+0.673
lers+0.635
y+0.615
ied+0.612
Neg logit contributions
 Deal-0.655
 pleasure-0.630
 Today-0.521
 welcome-0.509
 learn-0.489
Token to
Token ID284
Feature activation+3.81e+00

Pos logit contributions
 pleasure+0.286
 welcome+0.232
 Deal+0.231
 great+0.229
 think+0.225
Neg logit contributions
led-0.399
ed-0.332
ied-0.296
y-0.285
les-0.282
Token do
Token ID466
Feature activation-7.04e+00

Pos logit contributions
led+0.302
ed+0.251
y+0.251
ling+0.240
les+0.239
Neg logit contributions
 pleasure-0.162
 Deal-0.138
 Not-0.096
 OK-0.096
 Okay-0.096
Token.
Token ID13
Feature activation+5.54e+00

Pos logit contributions
 pleasure+0.412
 Deal+0.358
 learn+0.346
 welcome+0.345
 think+0.343
Neg logit contributions
led-0.459
ed-0.366
ied-0.322
y-0.322
les-0.307
Token.
Token ID13
Feature activation+5.29e+00

Pos logit contributions
led+0.137
ed+0.108
ied+0.099
awed+0.095
ling+0.094
Neg logit contributions
 pleasure-0.101
 welcome-0.082
 fun-0.073
 Deal-0.073
 Today-0.073
Token He
Token ID679
Feature activation+2.12e+00

Pos logit contributions
led+0.336
ed+0.306
y+0.285
ted+0.265
med+0.260
Neg logit contributions
 pleasure-0.239
 Deal-0.235
 great-0.189
 think-0.186
 learn-0.186
Token could
Token ID714
Feature activation+1.03e+01

Pos logit contributions
led+0.159
ed+0.134
ing+0.127
ier+0.126
ied+0.126
Neg logit contributions
 pleasure-0.090
 great-0.079
 think-0.078
 learn-0.078
 know-0.076
Token speak
Token ID2740
Feature activation-4.51e+00

Pos logit contributions
led+0.815
ed+0.684
y+0.617
ling+0.610
ied+0.604
Neg logit contributions
 pleasure-0.458
 Deal-0.402
 OK-0.315
 welcome-0.303
 Okay-0.293
Token and
Token ID290
Feature activation-4.28e+00

Pos logit contributions
 pleasure+0.261
 Deal+0.236
 welcome+0.209
 learn+0.201
 think+0.200
Neg logit contributions
led-0.310
ed-0.254
ied-0.222
y-0.220
les-0.213
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
 pleasure+0.173
 Deal+0.157
 OK+0.116
 welcome+0.113
 Today+0.110
Neg logit contributions
led-0.356
ed-0.305
y-0.278
ling-0.269
ied-0.268
Token in
Token ID287
Feature activation+1.20e+01

Pos logit contributions
 pleasure+1.328
 Deal+1.141
 welcome+1.065
 learn+1.023
 great+1.005
Neg logit contributions
led-1.724
ed-1.416
y-1.244
ied-1.241
ling-1.195
Token ways
Token ID2842
Feature activation-7.63e+00

Pos logit contributions
led+0.805
ed+0.658
y+0.611
es+0.605
med+0.596
Neg logit contributions
 pleasure-0.599
 Deal-0.571
 Today-0.457
 welcome-0.433
 Okay-0.433
Token that
Token ID326
Feature activation+5.78e-01

Pos logit contributions
 pleasure+0.421
 Deal+0.349
 welcome+0.348
 learn+0.336
 think+0.329
Neg logit contributions
led-0.552
ed-0.441
ied-0.388
awed-0.381
les-0.376
Token other
Token ID584
Feature activation+9.73e-01

Pos logit contributions
led+0.046
ed+0.039
ied+0.035
y+0.035
les+0.034
Neg logit contributions
 pleasure-0.027
 Deal-0.023
 welcome-0.020
 learn-0.019
 think-0.019
Token caul
Token ID46087
Feature activation+8.55e+00

Pos logit contributions
led+0.072
ed+0.060
ied+0.054
y+0.052
les+0.051
Neg logit contributions
 pleasure-0.051
 Deal-0.044
 welcome-0.040
 learn-0.038
 think-0.038
Token "
Token ID366
Feature activation-7.10e-01

Pos logit contributions
 pleasure+0.229
 Deal+0.195
 welcome+0.168
 learn+0.159
 know+0.156
Neg logit contributions
led-0.428
ed-0.368
ied-0.327
y-0.325
med-0.318
TokenBe
Token ID3856
Feature activation-1.64e+00

Pos logit contributions
 pleasure+0.037
 Deal+0.033
 welcome+0.029
 learn+0.028
 think+0.028
Neg logit contributions
led-0.053
ed-0.044
ied-0.039
y-0.038
les-0.037
Token smart
Token ID4451
Feature activation-4.08e+00

Pos logit contributions
 pleasure+0.072
 Deal+0.062
 Today+0.051
 Not+0.051
 welcome+0.050
Neg logit contributions
led-0.137
ed-0.115
ied-0.103
ling-0.101
y-0.100
Token and
Token ID290
Feature activation-4.04e+00

Pos logit contributions
 pleasure+0.207
 Deal+0.174
 welcome+0.165
 learn+0.153
 think+0.152
Neg logit contributions
led-0.312
ed-0.255
ied-0.232
we-0.221
y-0.221
Token always
Token ID1464
Feature activation-2.79e+00

Pos logit contributions
 pleasure+0.148
 Deal+0.137
 Today+0.106
 welcome+0.096
 OK+0.094
Neg logit contributions
led-0.344
ed-0.296
ied-0.262
y-0.256
ing-0.254
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
 pleasure+0.092
 Deal+0.083
 Today+0.059
 Not+0.057
 welcome+0.053
Neg logit contributions
led-0.244
ed-0.213
y-0.193
ling-0.186
ied-0.185
Token before
Token ID878
Feature activation+2.41e+00

Pos logit contributions
 pleasure+1.366
 Deal+1.215
 welcome+1.093
 learn+1.058
 think+1.047
Neg logit contributions
led-1.684
ed-1.380
ied-1.216
y-1.199
les-1.162
Token you
Token ID345
Feature activation-8.54e+00

Pos logit contributions
led+0.191
ed+0.161
y+0.146
ied+0.145
ing+0.144
Neg logit contributions
 pleasure-0.105
 Deal-0.093
 welcome-0.072
 think-0.069
 learn-0.069
Token make
Token ID787
Feature activation-5.34e+00

Pos logit contributions
 pleasure+0.312
 Deal+0.260
 welcome+0.205
 OK+0.189
 learn+0.185
Neg logit contributions
led-0.759
ed-0.658
y-0.595
ied-0.587
les-0.581
Token a
Token ID257
Feature activation-4.11e+00

Pos logit contributions
 pleasure+0.255
 Deal+0.243
 Today+0.196
 welcome+0.194
 Okay+0.183
Neg logit contributions
led-0.386
ed-0.323
ing-0.302
les-0.300
med-0.291
Token decision
Token ID2551
Feature activation-9.86e+00

Pos logit contributions
 pleasure+0.161
 Deal+0.157
 Today+0.119
 OK+0.118
 Not+0.118
Neg logit contributions
led-0.298
ed-0.255
y-0.255
ling-0.249
ing-0.245
Token rep
Token ID1128
Feature activation+5.20e-01

Pos logit contributions
led+0.167
ed+0.139
y+0.123
ied+0.123
ing+0.118
Neg logit contributions
 pleasure-0.123
 Deal-0.109
 welcome-0.096
 learn-0.093
 think-0.091
Tokenlying
Token ID3157
Feature activation-7.74e-01

Pos logit contributions
led+0.038
ed+0.031
ied+0.028
we+0.027
y+0.026
Neg logit contributions
 pleasure-0.028
 Deal-0.025
 welcome-0.022
 learn-0.022
 think-0.021
Token,
Token ID11
Feature activation-5.17e+00

Pos logit contributions
 pleasure+0.028
 Deal+0.021
 welcome+0.021
 OK+0.020
 learn+0.019
Neg logit contributions
led-0.069
ed-0.056
ied-0.054
les-0.053
lers-0.053
Token "
Token ID366
Feature activation-6.93e-01

Pos logit contributions
 pleasure+0.239
 Deal+0.211
 welcome+0.181
 learn+0.173
 know+0.171
Neg logit contributions
led-0.408
ed-0.353
y-0.309
ied-0.304
ing-0.300
TokenI
Token ID40
Feature activation+8.04e+00

Pos logit contributions
 pleasure+0.039
 Deal+0.035
 welcome+0.031
 learn+0.030
 think+0.030
Neg logit contributions
led-0.048
ed-0.040
y-0.035
ied-0.035
we-0.034
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
led+0.692
ed+0.605
y+0.553
ied+0.526
les+0.526
Neg logit contributions
 pleasure-0.303
 Deal-0.274
 welcome-0.207
 OK-0.190
 Not-0.187
Token it
Token ID340
Feature activation-4.58e+00

Pos logit contributions
 pleasure+1.007
 Deal+0.850
 welcome+0.735
 learn+0.698
 think+0.686
Neg logit contributions
led-2.047
ed-1.742
ied-1.575
y-1.562
les-1.522
Token's
Token ID338
Feature activation+4.32e+00

Pos logit contributions
 pleasure+0.241
 Deal+0.206
 welcome+0.193
 think+0.191
 learn+0.188
Neg logit contributions
led-0.331
ed-0.272
ied-0.249
y-0.235
med-0.231
Token a
Token ID257
Feature activation-4.09e+00

Pos logit contributions
led+0.353
ed+0.298
y+0.275
ied+0.273
ling+0.263
Neg logit contributions
 pleasure-0.177
 Deal-0.162
 learn-0.130
 welcome-0.128
 know-0.125
Token boun
Token ID31283
Feature activation+7.20e+00

Pos logit contributions
 Deal+0.173
 pleasure+0.163
 know+0.134
 Not+0.133
 learn+0.133
Neg logit contributions
led-0.272
y-0.239
ed-0.236
ling-0.212
lers-0.211
Tokency
Token ID948
Feature activation+6.54e+00

Pos logit contributions
led+0.433
ed+0.332
ied+0.292
es+0.277
we+0.277
Neg logit contributions
 pleasure-0.483
 Deal-0.414
 welcome-0.405
 think-0.380
 Today-0.376
Token,
Token ID11
Feature activation-5.15e+00

Pos logit contributions
led+0.109
ed+0.086
ied+0.081
awed+0.078
les+0.078
Neg logit contributions
 pleasure-0.072
 welcome-0.055
 learn-0.054
 great-0.053
 name-0.053
Token saying
Token ID2282
Feature activation-5.33e+00

Pos logit contributions
 pleasure+0.275
 Deal+0.244
 welcome+0.217
 learn+0.209
 think+0.206
Neg logit contributions
led-0.378
ed-0.313
ied-0.276
y-0.274
les-0.265
Token,
Token ID11
Feature activation-5.15e+00

Pos logit contributions
 pleasure+0.250
 Deal+0.216
 welcome+0.190
 learn+0.182
 think+0.179
Neg logit contributions
led-0.425
ed-0.358
ied-0.321
y-0.318
les-0.309
Token "
Token ID366
Feature activation-7.26e-01

Pos logit contributions
 pleasure+0.248
 Deal+0.214
 welcome+0.189
 know+0.179
 learn+0.179
Neg logit contributions
led-0.395
ed-0.342
y-0.299
ied-0.295
ing-0.293
TokenI
Token ID40
Feature activation+8.06e+00

Pos logit contributions
 pleasure+0.039
 Deal+0.034
 welcome+0.031
 learn+0.030
 think+0.029
Neg logit contributions
led-0.053
ed-0.044
ied-0.039
y-0.039
les-0.037
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
led+0.672
ed+0.582
y+0.528
ied+0.509
les+0.503
Neg logit contributions
 pleasure-0.329
 Deal-0.301
 welcome-0.234
 OK-0.215
 learn-0.215
Token I
Token ID314
Feature activation-2.61e+00

Pos logit contributions
 pleasure+0.999
 Deal+0.861
 welcome+0.724
 learn+0.695
 think+0.681
Neg logit contributions
led-2.044
ed-1.745
ied-1.578
y-1.563
les-1.523
Token know
Token ID760
Feature activation-1.84e+01

Pos logit contributions
 pleasure+0.141
 Deal+0.124
 welcome+0.111
 learn+0.107
 think+0.105
Neg logit contributions
led-0.189
ed-0.157
ied-0.138
y-0.137
les-0.133
Token where
Token ID810
Feature activation-4.29e+00

Pos logit contributions
 pleasure+0.854
 Deal+0.674
 welcome+0.653
 OK+0.617
 learn+0.606
Neg logit contributions
led-1.497
ed-1.248
ied-1.125
y-1.110
ling-1.100
Token your
Token ID534
Feature activation-6.91e+00

Pos logit contributions
 pleasure+0.166
 Deal+0.132
 welcome+0.123
 learn+0.116
 think+0.113
Neg logit contributions
led-0.379
ed-0.322
ied-0.292
y-0.291
ling-0.286
Token umbrella
Token ID25510
Feature activation-2.60e+00

Pos logit contributions
 pleasure+0.364
 Deal+0.343
 welcome+0.295
 learn+0.290
 Not+0.286
Neg logit contributions
led-0.488
ed-0.410
ied-0.357
y-0.354
lers-0.342
Token got
Token ID1392
Feature activation+3.33e+00

Pos logit contributions
 pleasure+0.198
 Deal+0.175
 welcome+0.156
 learn+0.150
 think+0.148
Neg logit contributions
led-0.276
ed-0.229
ied-0.202
y-0.201
les-0.194
Token it
Token ID340
Feature activation-4.82e+00

Pos logit contributions
led+0.276
ed+0.230
y+0.210
ied+0.208
ling+0.205
Neg logit contributions
 pleasure-0.147
 Deal-0.119
 welcome-0.111
 learn-0.106
 know-0.106
Token today
Token ID1909
Feature activation-8.05e+00

Pos logit contributions
 pleasure+0.275
 welcome+0.229
 Deal+0.229
 think+0.218
 OK+0.217
Neg logit contributions
led-0.329
ed-0.259
ied-0.234
les-0.227
awed-0.227
Token!
Token ID0
Feature activation+2.23e+00

Pos logit contributions
 pleasure+0.452
 Deal+0.386
 welcome+0.367
 learn+0.349
 think+0.345
Neg logit contributions
led-0.568
ed-0.460
ied-0.409
y-0.392
ling-0.390
Token I
Token ID314
Feature activation-2.65e+00

Pos logit contributions
led+0.151
ed+0.145
med+0.125
y+0.123
es+0.123
Neg logit contributions
 pleasure-0.097
 plan-0.080
 great-0.077
 Deal-0.075
 deal-0.075
Token think
Token ID892
Feature activation-2.42e+01

Pos logit contributions
 pleasure+0.110
 Deal+0.096
 welcome+0.080
 learn+0.075
 OK+0.074
Neg logit contributions
led-0.223
ed-0.191
y-0.172
ied-0.170
les-0.167
Token it
Token ID340
Feature activation-4.77e+00

Pos logit contributions
 pleasure+1.083
 Deal+0.928
 welcome+0.811
 learn+0.774
 think+0.762
Neg logit contributions
led-1.971
ed-1.666
ied-1.499
y-1.486
les-1.446
Token would
Token ID561
Feature activation+6.47e+00

Pos logit contributions
 pleasure+0.265
 Deal+0.227
 think+0.214
 welcome+0.213
 learn+0.210
Neg logit contributions
led-0.328
ed-0.265
ied-0.243
y-0.229
ling-0.226
Token be
Token ID307
Feature activation-1.40e+01

Pos logit contributions
led+0.508
ed+0.432
y+0.423
ied+0.397
ling+0.396
Neg logit contributions
 pleasure-0.233
 Deal-0.231
 Today-0.156
 Okay-0.151
 First-0.147
Token perfect
Token ID2818
Feature activation-3.71e+00

Pos logit contributions
 pleasure+0.537
 Deal+0.442
 welcome+0.380
 learn+0.356
 think+0.350
Neg logit contributions
led-1.231
ed-1.057
ied-0.960
y-0.952
les-0.929
Token for
Token ID329
Feature activation+1.43e+00

Pos logit contributions
 pleasure+0.200
 Deal+0.168
 welcome+0.159
 OK+0.150
 think+0.149
Neg logit contributions
led-0.274
ed-0.223
ied-0.200
y-0.192
les-0.191
Token all
Token ID477
Feature activation-1.34e+00

Pos logit contributions
 pleasure+0.216
 welcome+0.171
 Deal+0.169
 great+0.162
 think+0.160
Neg logit contributions
led-0.367
ed-0.303
ied-0.280
we-0.269
les-0.268
Token,
Token ID11
Feature activation-5.16e+00

Pos logit contributions
 pleasure+0.065
 welcome+0.055
 think+0.050
 learn+0.049
 Deal+0.048
Neg logit contributions
led-0.102
ed-0.088
ked-0.077
we-0.077
awed-0.076
Token she
Token ID673
Feature activation+3.89e+00

Pos logit contributions
 pleasure+0.272
 Deal+0.241
 welcome+0.214
 learn+0.206
 think+0.203
Neg logit contributions
led-0.381
ed-0.316
ied-0.280
y-0.277
les-0.268
Token couldn
Token ID3521
Feature activation+2.57e+00

Pos logit contributions
led+0.250
ed+0.201
ied+0.185
ing+0.177
ted+0.173
Neg logit contributions
 pleasure-0.212
 think-0.187
 learn-0.183
 Deal-0.181
 know-0.180
Token't
Token ID470
Feature activation-3.58e+00

Pos logit contributions
led+0.227
ed+0.199
y+0.181
ied+0.180
les+0.176
Neg logit contributions
 pleasure-0.097
 Deal-0.077
 welcome-0.064
 think-0.058
 learn-0.057
Token think
Token ID892
Feature activation-2.41e+01

Pos logit contributions
 pleasure+0.123
 Deal+0.102
 welcome+0.078
 OK+0.070
 Not+0.068
Neg logit contributions
led-0.321
ed-0.278
y-0.257
ied-0.250
les-0.250
Token of
Token ID286
Feature activation+1.31e+01

Pos logit contributions
 pleasure+1.328
 Deal+1.140
 welcome+1.064
 learn+1.028
 think+1.016
Neg logit contributions
led-1.734
ed-1.422
y-1.236
ied-1.232
ling-1.202
Token anything
Token ID1997
Feature activation-5.45e+00

Pos logit contributions
led+0.935
ed+0.770
y+0.704
ied+0.692
lers+0.690
Neg logit contributions
 pleasure-0.606
 Deal-0.596
 welcome-0.487
 learn-0.483
 Today-0.483
Token good
Token ID922
Feature activation-5.78e+00

Pos logit contributions
 pleasure+0.298
 great+0.248
 welcome+0.246
 think+0.239
 Deal+0.237
Neg logit contributions
led-0.380
ed-0.314
ied-0.281
awed-0.267
y-0.265
Token.
Token ID13
Feature activation+5.71e+00

Pos logit contributions
 pleasure+0.333
 welcome+0.279
 Deal+0.273
 think+0.269
 OK+0.260
Neg logit contributions
led-0.384
ed-0.306
ied-0.280
med-0.277
awed-0.272
Token Everything
Token ID11391
Feature activation-4.46e+00

Pos logit contributions
led+0.384
ed+0.371
y+0.306
als+0.304
ted+0.304
Neg logit contributions
 pleasure-0.240
 Deal-0.218
 deal-0.210
 plan-0.206
 learn-0.201
Token of
Token ID286
Feature activation+1.31e+01

Pos logit contributions
 pleasure+0.552
 welcome+0.452
 great+0.452
 learn+0.432
 OK+0.419
Neg logit contributions
led-0.773
ed-0.604
awed-0.555
lers-0.553
ied-0.547
Token it
Token ID340
Feature activation-4.61e+00

Pos logit contributions
led+0.936
ed+0.775
ied+0.701
y+0.693
med+0.675
Neg logit contributions
 pleasure-0.688
 Deal-0.627
 welcome-0.531
 know-0.515
 OK-0.511
Token.
Token ID13
Feature activation+5.66e+00

Pos logit contributions
 pleasure+0.253
 welcome+0.216
 great+0.214
 think+0.214
 learn+0.213
Neg logit contributions
led-0.306
ed-0.247
ied-0.230
awed-0.215
lers-0.211
Token Molly
Token ID30236
Feature activation+1.32e+00

Pos logit contributions
led+0.411
ed+0.372
y+0.335
les+0.320
ied+0.319
Neg logit contributions
 pleasure-0.239
 Deal-0.202
 welcome-0.188
 OK-0.185
 know-0.182
Token would
Token ID561
Feature activation+6.44e+00

Pos logit contributions
led+0.088
ed+0.071
ied+0.064
ier+0.060
we+0.060
Neg logit contributions
 pleasure-0.075
 Deal-0.064
 learn-0.063
 think-0.062
 know-0.061
Token think
Token ID892
Feature activation-2.41e+01

Pos logit contributions
led+0.501
ed+0.430
y+0.410
ied+0.396
les+0.392
Neg logit contributions
 pleasure-0.255
 Deal-0.236
 OK-0.180
 welcome-0.171
 Okay-0.167
Token a
Token ID257
Feature activation-4.08e+00

Pos logit contributions
 pleasure+1.272
 Deal+1.079
 welcome+1.000
 learn+0.979
 great+0.961
Neg logit contributions
led-1.778
ed-1.475
y-1.288
ied-1.282
ling-1.243
Token lot
Token ID1256
Feature activation-1.05e+01

Pos logit contributions
 Deal+0.136
 pleasure+0.134
 OK+0.097
 welcome+0.090
 Today+0.089
Neg logit contributions
led-0.326
y-0.284
ed-0.281
ling-0.268
les-0.261
Token about
Token ID546
Feature activation+1.44e+00

Pos logit contributions
 pleasure+0.560
 welcome+0.470
 Deal+0.454
 learn+0.447
 great+0.440
Neg logit contributions
led-0.753
ed-0.614
awed-0.538
ied-0.527
we-0.525
Token her
Token ID607
Feature activation+2.21e+00

Pos logit contributions
led+0.109
ed+0.092
y+0.083
ied+0.082
les+0.080
Neg logit contributions
 pleasure-0.069
 Deal-0.064
 welcome-0.053
 OK-0.050
 learn-0.049
Token team
Token ID1074
Feature activation-2.47e+00

Pos logit contributions
led+0.184
ed+0.158
y+0.144
ied+0.139
ling+0.138
Neg logit contributions
 pleasure-0.086
 Deal-0.080
 welcome-0.064
 know-0.061
 OK-0.061
Token asked
Token ID1965
Feature activation+2.41e+00

Pos logit contributions
 pleasure+0.253
 Deal+0.216
 welcome+0.206
 think+0.200
 learn+0.198
Neg logit contributions
led-0.279
ed-0.221
ied-0.201
y-0.197
ling-0.192
Token,
Token ID11
Feature activation-5.34e+00

Pos logit contributions
led+0.199
ed+0.166
ied+0.150
y+0.149
les+0.147
Neg logit contributions
 pleasure-0.107
 Deal-0.090
 welcome-0.082
 learn-0.077
 think-0.076
Token "
Token ID366
Feature activation-8.68e-01

Pos logit contributions
 pleasure+0.251
 Deal+0.222
 learn+0.185
 welcome+0.183
 know+0.180
Neg logit contributions
led-0.410
ed-0.360
y-0.317
ied-0.309
ing-0.307
TokenDo
Token ID5211
Feature activation+9.93e-01

Pos logit contributions
 pleasure+0.046
 Deal+0.040
 welcome+0.036
 learn+0.035
 know+0.034
Neg logit contributions
led-0.063
ed-0.053
y-0.047
ied-0.046
les-0.045
Token you
Token ID345
Feature activation-8.57e+00

Pos logit contributions
led+0.074
ed+0.062
ied+0.057
y+0.056
ing+0.055
Neg logit contributions
 pleasure-0.047
 Deal-0.042
 welcome-0.032
 Okay-0.031
 Promise-0.031
Token think
Token ID892
Feature activation-2.41e+01

Pos logit contributions
 pleasure+0.401
 Deal+0.374
 purpose+0.296
 Okay+0.294
 Not+0.290
Neg logit contributions
led-0.557
ed-0.487
y-0.476
les-0.439
ly-0.421
Token it
Token ID340
Feature activation-4.66e+00

Pos logit contributions
 pleasure+1.171
 Deal+1.041
 welcome+0.880
 learn+0.852
 think+0.841
Neg logit contributions
led-1.872
ed-1.574
ied-1.419
y-1.412
les-1.367
Token wants
Token ID3382
Feature activation-2.48e+00

Pos logit contributions
 pleasure+0.272
 Deal+0.245
 welcome+0.215
 learn+0.209
 OK+0.205
Neg logit contributions
led-0.321
ed-0.263
y-0.230
ied-0.225
les-0.221
Token to
Token ID284
Feature activation+3.71e+00

Pos logit contributions
 pleasure+0.155
 Deal+0.147
 welcome+0.122
 learn+0.120
 think+0.120
Neg logit contributions
led-0.153
ed-0.126
y-0.110
ied-0.108
les-0.103
Token play
Token ID711
Feature activation-9.22e+00

Pos logit contributions
led+0.239
ed+0.214
y+0.212
les+0.200
ied+0.193
Neg logit contributions
 pleasure-0.160
 Deal-0.150
 Not-0.108
 Promise-0.103
 Okay-0.102
Token?"
Token ID1701
Feature activation-5.85e+00

Pos logit contributions
 pleasure+0.551
 Deal+0.495
 know+0.417
 welcome+0.415
 Not+0.408
Neg logit contributions
led-0.611
ed-0.500
y-0.445
les-0.435
med-0.432
Token Mr
Token ID1770
Feature activation+1.57e+00

Pos logit contributions
 pleasure+0.230
 Deal+0.205
 learn+0.168
 welcome+0.160
 know+0.160
Neg logit contributions
led-0.420
ed-0.354
y-0.329
ied-0.318
ling-0.317
Token.
Token ID13
Feature activation+5.45e+00

Pos logit contributions
led+0.108
ied+0.087
ed+0.083
med+0.079
ted+0.076
Neg logit contributions
 pleasure-0.088
 welcome-0.077
 Deal-0.076
 OK-0.073
 think-0.069
Token Dragon
Token ID2851
Feature activation+6.45e+00

Pos logit contributions
led+0.412
ed+0.335
ied+0.306
y+0.294
les+0.292
Neg logit contributions
 pleasure-0.284
 Deal-0.250
 welcome-0.225
 OK-0.213
 think-0.211
Token.
Token ID13
Feature activation+5.44e+00

Pos logit contributions
led+0.486
ed+0.402
ied+0.372
ted+0.349
med+0.347
Neg logit contributions
 pleasure-0.327
 Deal-0.269
 welcome-0.268
 think-0.251
 OK-0.246
Token I
Token ID314
Feature activation-2.70e+00

Pos logit contributions
led+0.420
ed+0.375
y+0.328
ing+0.319
ted+0.315
Neg logit contributions
 pleasure-0.233
 Deal-0.198
 great-0.176
 learn-0.176
 welcome-0.169
Token think
Token ID892
Feature activation-2.41e+01

Pos logit contributions
 pleasure+0.117
 Deal+0.102
 welcome+0.085
 learn+0.080
 Not+0.078
Neg logit contributions
led-0.224
ed-0.191
y-0.172
ied-0.169
les-0.166
Token you
Token ID345
Feature activation-8.63e+00

Pos logit contributions
 pleasure+0.940
 Deal+0.801
 welcome+0.664
 learn+0.635
 think+0.622
Neg logit contributions
led-2.102
ed-1.800
ied-1.636
y-1.619
les-1.582
Token're
Token ID821
Feature activation-9.91e+00

Pos logit contributions
 pleasure+0.373
 Deal+0.323
 welcome+0.275
 learn+0.259
 think+0.253
Neg logit contributions
led-0.719
ed-0.611
ied-0.548
y-0.546
les-0.532
Token cool
Token ID3608
Feature activation-8.41e+00

Pos logit contributions
 pleasure+0.438
 Deal+0.385
 learn+0.316
 welcome+0.307
 Today+0.307
Neg logit contributions
led-0.802
ed-0.676
y-0.605
ied-0.605
ling-0.598
Token."
Token ID526
Feature activation-2.33e+00

Pos logit contributions
 pleasure+0.433
 Deal+0.352
 welcome+0.346
 OK+0.331
 think+0.318
Neg logit contributions
led-0.626
ed-0.499
ied-0.476
med-0.450
awed-0.450
Token The
Token ID383
Feature activation+2.60e+00

Pos logit contributions
 pleasure+0.081
 Deal+0.067
 welcome+0.053
 great+0.051
 learn+0.050
Neg logit contributions
led-0.212
ed-0.188
y-0.166
ted-0.163
les-0.163
Tokenla
Token ID5031
Feature activation+1.64e+01

Pos logit contributions
 pleasure+0.068
 Deal+0.058
 welcome+0.058
 know+0.056
 OK+0.055
Neg logit contributions
led-0.056
ed-0.040
ied-0.033
lers-0.033
ling-0.032
Token!
Token ID0
Feature activation+2.20e+00

Pos logit contributions
led+1.301
ed+1.069
ied+0.984
ted+0.934
les+0.929
Neg logit contributions
 pleasure-0.785
 welcome-0.637
 Deal-0.622
 think-0.582
 know-0.579
Token What
Token ID1867
Feature activation-5.36e+00

Pos logit contributions
led+0.161
ed+0.151
y+0.131
ted+0.127
med+0.126
Neg logit contributions
 pleasure-0.094
 Deal-0.083
 learn-0.073
 great-0.072
 deal-0.072
Token do
Token ID466
Feature activation-7.03e+00

Pos logit contributions
 pleasure+0.251
 Deal+0.230
 welcome+0.182
 learn+0.174
 OK+0.173
Neg logit contributions
led-0.419
ed-0.358
y-0.322
ied-0.317
es-0.306
Token you
Token ID345
Feature activation-8.56e+00

Pos logit contributions
 pleasure+0.271
 Deal+0.231
 welcome+0.182
 learn+0.174
 think+0.172
Neg logit contributions
led-0.613
ed-0.527
ied-0.480
y-0.474
we-0.464
Token think
Token ID892
Feature activation-2.41e+01

Pos logit contributions
 pleasure+0.332
 Deal+0.308
 Okay+0.230
 Sometimes+0.226
 Not+0.211
Neg logit contributions
led-0.693
ed-0.601
y-0.550
les-0.521
ling-0.519
Token that
Token ID326
Feature activation+6.25e-01

Pos logit contributions
 pleasure+1.143
 Deal+0.998
 welcome+0.864
 learn+0.831
 think+0.818
Neg logit contributions
led-1.907
ed-1.606
ied-1.442
y-1.428
les-1.387
Token is
Token ID318
Feature activation-2.42e+00

Pos logit contributions
led+0.047
ed+0.039
y+0.036
ing+0.035
ied+0.034
Neg logit contributions
 pleasure-0.031
 Deal-0.029
 learn-0.022
 welcome-0.022
 OK-0.021
Token?"
Token ID1701
Feature activation-5.79e+00

Pos logit contributions
 pleasure+0.119
 Deal+0.108
 welcome+0.091
 learn+0.089
 know+0.087
Neg logit contributions
led-0.184
ed-0.154
ied-0.139
y-0.138
ling-0.132
Token Kay
Token ID17356
Feature activation-1.01e+00

Pos logit contributions
 pleasure+0.225
 Deal+0.196
 welcome+0.156
 OK+0.146
 learn+0.145
Neg logit contributions
led-0.487
ed-0.442
y-0.393
ied-0.384
ted-0.379
Tokenla
Token ID5031
Feature activation+1.63e+01

Pos logit contributions
 pleasure+0.066
 Deal+0.059
 think+0.058
 +0.058
 know+0.057
Neg logit contributions
led-0.051
ed-0.036
lers-0.031
ied-0.031
ier-0.030
Token,
Token ID11
Feature activation-5.32e+00

Pos logit contributions
led+0.300
ed+0.243
ied+0.239
med+0.222
ling+0.222
Neg logit contributions
 pleasure-0.152
 Deal-0.117
 welcome-0.116
 think-0.109
 learn-0.109
Token so
Token ID523
Feature activation-1.08e+01

Pos logit contributions
 pleasure+0.234
 Deal+0.213
 welcome+0.172
 learn+0.164
 know+0.161
Neg logit contributions
led-0.432
ed-0.367
y-0.332
ied-0.332
we-0.318
Token she
Token ID673
Feature activation+3.91e+00

Pos logit contributions
 pleasure+0.654
 Deal+0.592
 welcome+0.530
 learn+0.515
 think+0.509
Neg logit contributions
led-0.717
ed-0.583
ied-0.507
y-0.501
les-0.477
Token couldn
Token ID3521
Feature activation+2.73e+00

Pos logit contributions
led+0.255
ed+0.204
ier+0.197
les+0.190
ling+0.190
Neg logit contributions
 pleasure-0.192
 think-0.177
 great-0.176
 know-0.172
 see-0.168
Token't
Token ID470
Feature activation-3.44e+00

Pos logit contributions
led+0.238
ed+0.211
y+0.190
ied+0.190
ing+0.185
Neg logit contributions
 pleasure-0.106
 Deal-0.085
 welcome-0.069
 OK-0.062
 think-0.062
Token think
Token ID892
Feature activation-2.41e+01

Pos logit contributions
 pleasure+0.134
 Deal+0.113
 welcome+0.092
 OK+0.082
 Not+0.079
Neg logit contributions
led-0.297
ed-0.258
y-0.236
ied-0.232
we-0.227
Token of
Token ID286
Feature activation+1.31e+01

Pos logit contributions
 pleasure+1.401
 Deal+1.217
 welcome+1.151
 learn+1.136
 know+1.115
Neg logit contributions
led-1.642
ed-1.326
y-1.147
ling-1.118
ied-1.110
Token a
Token ID257
Feature activation-4.32e+00

Pos logit contributions
led+0.858
ed+0.727
ied+0.657
we+0.650
y+0.647
Neg logit contributions
 Deal-0.638
 pleasure-0.631
 Today-0.510
 welcome-0.495
 deal-0.471
Token good
Token ID922
Feature activation-5.89e+00

Pos logit contributions
 pleasure+0.212
 Deal+0.199
 welcome+0.161
 learn+0.158
 OK+0.157
Neg logit contributions
led-0.311
ed-0.263
y-0.242
ied-0.234
les-0.230
Token idea
Token ID2126
Feature activation-1.33e+01

Pos logit contributions
 pleasure+0.190
 Deal+0.168
 welcome+0.121
 OK+0.117
 learn+0.115
Neg logit contributions
led-0.543
ed-0.475
y-0.437
ied-0.433
les-0.426
Token.
Token ID13
Feature activation+5.55e+00

Pos logit contributions
 pleasure+0.648
 welcome+0.585
 OK+0.565
 learn+0.556
 think+0.547
Neg logit contributions
led-1.005
ed-0.763
awed-0.714
ling-0.710
lers-0.697
Token then
Token ID788
Feature activation-9.23e+00

Pos logit contributions
 pleasure+0.176
 Deal+0.142
 think+0.140
 learn+0.136
 OK+0.136
Neg logit contributions
led-0.309
ed-0.261
ied-0.242
lers-0.238
les-0.238
Token said
Token ID531
Feature activation+6.50e-01

Pos logit contributions
 pleasure+0.430
 thank+0.360
 learn+0.358
 think+0.357
 great+0.355
Neg logit contributions
led-0.673
ed-0.535
ied-0.524
we-0.523
y-0.513
Token,
Token ID11
Feature activation-5.11e+00

Pos logit contributions
led+0.055
ed+0.046
ied+0.042
y+0.042
les+0.041
Neg logit contributions
 pleasure-0.027
 Deal-0.023
 welcome-0.020
 learn-0.019
 OK-0.019
Token "
Token ID366
Feature activation-6.42e-01

Pos logit contributions
 pleasure+0.229
 Deal+0.194
 welcome+0.169
 learn+0.161
 know+0.159
Neg logit contributions
led-0.417
ed-0.358
y-0.316
ied-0.315
ling-0.307
TokenI
Token ID40
Feature activation+8.17e+00

Pos logit contributions
 pleasure+0.033
 Deal+0.029
 welcome+0.025
 learn+0.025
 OK+0.025
Neg logit contributions
led-0.048
ed-0.039
ied-0.035
lers-0.035
y-0.034
Token think
Token ID892
Feature activation-2.41e+01

Pos logit contributions
led+0.654
ed+0.594
y+0.559
les+0.509
ied+0.503
Neg logit contributions
 pleasure-0.295
 Deal-0.287
 welcome-0.203
 Not-0.184
 Today-0.181
Token I
Token ID314
Feature activation-2.58e+00

Pos logit contributions
 pleasure+0.986
 Deal+0.833
 welcome+0.715
 learn+0.678
 think+0.666
Neg logit contributions
led-2.063
ed-1.758
ied-1.592
y-1.578
les-1.539
Token can
Token ID460
Feature activation-3.58e+00

Pos logit contributions
 pleasure+0.144
 Deal+0.131
 welcome+0.114
 learn+0.108
 OK+0.107
Neg logit contributions
led-0.180
ed-0.150
y-0.132
ied-0.130
les-0.125
Token help
Token ID1037
Feature activation-8.09e+00

Pos logit contributions
 pleasure+0.146
 Deal+0.125
 welcome+0.094
 OK+0.090
 Today+0.087
Neg logit contributions
led-0.289
ed-0.255
y-0.234
ied-0.228
les-0.225
Token."
Token ID526
Feature activation-2.23e+00

Pos logit contributions
 pleasure+0.354
 Deal+0.306
 welcome+0.244
 Today+0.231
 think+0.223
Neg logit contributions
led-0.660
ed-0.566
y-0.521
ied-0.513
we-0.510
Token
Token ID198
Feature activation-9.33e+00

Pos logit contributions
 pleasure+0.088
 Deal+0.071
 welcome+0.060
 great+0.056
 think+0.056
Neg logit contributions
led-0.191
ed-0.170
y-0.149
les-0.147
ied-0.144
Token went
Token ID1816
Feature activation+8.92e+00

Pos logit contributions
led+0.017
ed+0.013
ied+0.013
we+0.012
les+0.012
Neg logit contributions
 pleasure-0.013
 Deal-0.012
 think-0.012
 welcome-0.012
 learn-0.011
Token to
Token ID284
Feature activation+4.11e+00

Pos logit contributions
led+0.602
ed+0.483
ied+0.423
y+0.418
les+0.406
Neg logit contributions
 pleasure-0.528
 Deal-0.472
 welcome-0.440
 learn-0.428
 think-0.421
Token Sue
Token ID26089
Feature activation-1.88e+00

Pos logit contributions
led+0.191
ed+0.160
ted+0.140
y+0.139
 behind+0.134
Neg logit contributions
 pleasure-0.256
 Deal-0.241
mmm-0.207
 Today-0.202
 Not-0.200
Token and
Token ID290
Feature activation-3.77e+00

Pos logit contributions
 pleasure+0.113
 Deal+0.102
 welcome+0.091
 learn+0.087
 OK+0.087
Neg logit contributions
led-0.124
ed-0.101
y-0.089
ied-0.088
ling-0.085
Token bark
Token ID21405
Feature activation+2.38e+00

Pos logit contributions
 pleasure+0.194
 think+0.167
 learn+0.164
 welcome+0.163
 Deal+0.163
Neg logit contributions
led-0.270
ed-0.219
ied-0.202
les-0.198
y-0.195
Tokened
Token ID276
Feature activation+1.97e+01

Pos logit contributions
led+0.058
web+0.036
ied+0.031
we+0.031
lers+0.024
Neg logit contributions
 pleasure-0.204
 OK-0.194
 okay-0.193
 great-0.189
 welcome-0.185
Token.
Token ID13
Feature activation+5.90e+00

Pos logit contributions
led+1.353
ed+1.084
ied+0.993
y+0.947
we+0.946
Neg logit contributions
 pleasure-1.150
 Deal-0.992
 welcome-0.950
 OK-0.905
 learn-0.902
Token Sue
Token ID26089
Feature activation-1.81e+00

Pos logit contributions
led+0.461
ed+0.405
ied+0.345
y+0.344
ted+0.342
Neg logit contributions
 pleasure-0.277
 Deal-0.239
 welcome-0.200
 learn-0.199
 think-0.198
Token knew
Token ID2993
Feature activation+2.19e+00

Pos logit contributions
 pleasure+0.090
 think+0.082
 learn+0.081
 know+0.079
 Deal+0.077
Neg logit contributions
led-0.125
ed-0.101
ied-0.095
ier-0.091
we-0.090
Token what
Token ID644
Feature activation-9.51e+00

Pos logit contributions
led+0.179
ed+0.150
y+0.135
ied+0.133
les+0.132
Neg logit contributions
 pleasure-0.100
 Deal-0.082
 welcome-0.078
 OK-0.075
 learn-0.073
Token Spot
Token ID15899
Feature activation+3.49e-01

Pos logit contributions
 pleasure+0.481
 welcome+0.409
 Deal+0.397
 learn+0.389
 know+0.383
Neg logit contributions
led-0.739
ed-0.603
les-0.538
ling-0.530
ied-0.526
TokenCan
Token ID6090
Feature activation+3.92e+00

Pos logit contributions
led+0.198
ed+0.165
ied+0.151
y+0.148
ling+0.146
Neg logit contributions
 pleasure-0.115
 Deal-0.102
 welcome-0.089
 learn-0.085
 think-0.085
Token I
Token ID314
Feature activation-2.20e+00

Pos logit contributions
led+0.288
ed+0.244
y+0.215
ied+0.215
we+0.212
Neg logit contributions
 pleasure-0.204
 Deal-0.173
 welcome-0.149
 know-0.141
 learn-0.136
Token have
Token ID423
Feature activation-8.32e+00

Pos logit contributions
 pleasure+0.078
 Deal+0.065
 welcome+0.045
 Not+0.044
 OK+0.044
Neg logit contributions
led-0.193
ed-0.170
y-0.159
ied-0.152
les-0.152
Token the
Token ID262
Feature activation+3.22e+00

Pos logit contributions
 pleasure+0.401
 Deal+0.368
 welcome+0.303
 Today+0.290
 think+0.281
Neg logit contributions
led-0.633
ed-0.528
ted-0.484
med-0.479
lers-0.479
Token t
Token ID256
Feature activation-3.91e-03

Pos logit contributions
led+0.176
ed+0.142
y+0.127
lers+0.124
les+0.118
Neg logit contributions
 pleasure-0.200
 Deal-0.190
 learn-0.170
 Not-0.168
 know-0.168
Tokeneddy
Token ID21874
Feature activation+1.76e+01

Pos logit contributions
 pleasure+0.000
 Deal+0.000
 welcome+0.000
 Today+0.000
 know+0.000
Neg logit contributions
led-0.000
ed-0.000
ied-0.000
ils-0.000
ling-0.000
Token bear
Token ID6842
Feature activation+5.48e+00

Pos logit contributions
led+1.209
ed+0.987
ied+0.911
y+0.838
ing+0.819
Neg logit contributions
 pleasure-0.997
 Deal-0.880
 welcome-0.823
 think-0.786
 learn-0.782
Token,
Token ID11
Feature activation-4.72e+00

Pos logit contributions
led+0.454
ed+0.385
ied+0.347
y+0.343
les+0.335
Neg logit contributions
 pleasure-0.240
 Deal-0.205
 welcome-0.179
 learn-0.170
 think-0.167
Token L
Token ID406
Feature activation+3.28e+00

Pos logit contributions
 pleasure+0.200
 Deal+0.162
 know+0.133
 Today+0.131
 learn+0.130
Neg logit contributions
led-0.326
y-0.272
ed-0.271
ied-0.257
ted-0.256
Tokenila
Token ID10102
Feature activation+1.30e+01

Pos logit contributions
led+0.221
ed+0.179
lers+0.152
ted+0.148
med+0.148
Neg logit contributions
 pleasure-0.180
 Deal-0.165
 welcome-0.158
 think-0.152
 learn-0.150
Token?"
Token ID1701
Feature activation-5.49e+00

Pos logit contributions
led+1.193
ed+1.037
ied+0.948
med+0.913
ted+0.906
Neg logit contributions
 pleasure-0.435
 Deal-0.351
 welcome-0.337
 think-0.323
 learn-0.316
Token because
Token ID780
Feature activation-7.46e+00

Pos logit contributions
 pleasure+0.230
 Deal+0.199
 welcome+0.181
 learn+0.175
 think+0.175
Neg logit contributions
led-0.342
ed-0.282
ied-0.254
y-0.244
med-0.242
Token she
Token ID673
Feature activation+4.46e+00

Pos logit contributions
 pleasure+0.384
 Deal+0.331
 welcome+0.305
 learn+0.296
 think+0.289
Neg logit contributions
led-0.561
ed-0.464
ied-0.406
y-0.405
les-0.402
Token loved
Token ID6151
Feature activation+2.53e+00

Pos logit contributions
led+0.314
ed+0.260
ied+0.235
ing+0.227
ier+0.225
Neg logit contributions
 pleasure-0.234
 Deal-0.208
 think-0.197
 know-0.195
 learn-0.193
Token her
Token ID607
Feature activation+2.71e+00

Pos logit contributions
led+0.195
ed+0.163
ied+0.144
y+0.142
les+0.140
Neg logit contributions
 pleasure-0.127
 Deal-0.108
 welcome-0.099
 learn-0.096
 think-0.095
Token t
Token ID256
Feature activation+1.12e-01

Pos logit contributions
led+0.188
ed+0.153
y+0.135
ied+0.134
lers+0.129
Neg logit contributions
 pleasure-0.153
 Deal-0.141
 welcome-0.124
 learn-0.121
 think-0.119
Tokeneddy
Token ID21874
Feature activation+1.78e+01

Pos logit contributions
led+0.006
ed+0.004
ied+0.003
ils+0.003
med+0.003
Neg logit contributions
 pleasure-0.008
 Deal-0.007
 know-0.006
 welcome-0.006
 learn-0.006
Token bear
Token ID6842
Feature activation+5.65e+00

Pos logit contributions
led+1.180
ed+0.958
ied+0.852
y+0.815
les+0.787
Neg logit contributions
 pleasure-1.067
 Deal-0.949
 welcome-0.871
 learn-0.845
 think-0.837
Token very
Token ID845
Feature activation-5.31e+00

Pos logit contributions
led+0.464
ed+0.391
ied+0.360
we+0.344
les+0.343
Neg logit contributions
 pleasure-0.252
 Deal-0.202
 welcome-0.190
 learn-0.186
 great-0.184
Token much
Token ID881
Feature activation-3.49e+00

Pos logit contributions
 pleasure+0.165
 Deal+0.126
 welcome+0.105
 learn+0.102
 great+0.099
Neg logit contributions
led-0.503
ed-0.439
ied-0.401
y-0.395
les-0.389
Token.
Token ID13
Feature activation+5.85e+00

Pos logit contributions
 pleasure+0.206
 Deal+0.169
 welcome+0.168
 OK+0.162
 think+0.162
Neg logit contributions
led-0.239
ed-0.191
ied-0.177
we-0.167
med-0.166
Token
Token ID198
Feature activation-9.13e+00

Pos logit contributions
led+0.415
ed+0.386
ted+0.339
y+0.339
awed+0.327
Neg logit contributions
 pleasure-0.285
 Deal-0.242
 welcome-0.218
 deal-0.215
 great-0.203
Token Her
Token ID2332
Feature activation+4.87e+00

Pos logit contributions
led+0.430
ed+0.394
y+0.326
ted+0.310
ing+0.309
Neg logit contributions
 pleasure-0.365
 Deal-0.323
 deal-0.302
 learn-0.294
 plan-0.293
Token mom
Token ID1995
Feature activation-5.55e+00

Pos logit contributions
led+0.424
ed+0.366
y+0.328
ied+0.326
lers+0.322
Neg logit contributions
 pleasure-0.177
 Deal-0.149
 welcome-0.124
 learn-0.121
 think-0.118
Token smiled
Token ID13541
Feature activation+6.98e+00

Pos logit contributions
 pleasure+0.287
 think+0.247
 welcome+0.245
 learn+0.242
 know+0.240
Neg logit contributions
led-0.370
ed-0.290
ied-0.279
lers-0.270
ls-0.263
Token and
Token ID290
Feature activation-2.85e+00

Pos logit contributions
led+0.541
ed+0.434
ied+0.427
we+0.405
lers+0.404
Neg logit contributions
 pleasure-0.333
 Deal-0.290
 welcome-0.276
 OK-0.270
 okay-0.255
Token c
Token ID269
Feature activation+4.46e+00

Pos logit contributions
 pleasure+0.169
 Deal+0.146
 welcome+0.142
 think+0.137
 know+0.135
Neg logit contributions
led-0.183
ed-0.145
ied-0.138
y-0.134
ling-0.130
Tokenuddled
Token ID32745
Feature activation+1.78e+01

Pos logit contributions
led+0.181
y+0.134
ed+0.133
lers+0.120
ied+0.118
Neg logit contributions
 pleasure-0.312
 Deal-0.284
 OK-0.255
 great-0.250
 okay-0.250
Token her
Token ID607
Feature activation+3.42e+00

Pos logit contributions
led+1.289
ed+1.025
ied+0.994
y+0.948
les+0.947
Neg logit contributions
 pleasure-0.872
 Deal-0.736
 welcome-0.719
 learn-0.718
 think-0.705
Token too
Token ID1165
Feature activation-6.29e+00

Pos logit contributions
led+0.247
ed+0.205
ied+0.188
y+0.179
les+0.178
Neg logit contributions
 pleasure-0.184
 Deal-0.162
 welcome-0.148
 OK-0.146
 learn-0.145
Token.
Token ID13
Feature activation+6.91e+00

Pos logit contributions
 pleasure+0.410
 Deal+0.370
 welcome+0.344
 learn+0.339
 think+0.335
Neg logit contributions
led-0.381
ed-0.301
ied-0.265
y-0.251
les-0.248
Token They
Token ID1119
Feature activation-1.00e+00

Pos logit contributions
led+0.484
ed+0.435
y+0.364
ted+0.350
ing+0.347
Neg logit contributions
 pleasure-0.347
 Deal-0.300
 deal-0.279
 learn-0.271
 plan-0.268
Token were
Token ID547
Feature activation+2.22e+00

Pos logit contributions
 pleasure+0.056
 Deal+0.048
 learn+0.046
 think+0.046
 know+0.046
Neg logit contributions
led-0.068
ed-0.055
ied-0.051
ing-0.049
we-0.048
Token explore
Token ID7301
Feature activation-1.09e+01

Pos logit contributions
 pleasure+0.121
 Deal+0.105
 Today+0.076
 Not+0.074
 welcome+0.070
Neg logit contributions
led-0.286
ed-0.253
lers-0.219
y-0.217
ted-0.216
Token."
Token ID526
Feature activation-1.63e+00

Pos logit contributions
 pleasure+0.580
 Deal+0.512
 welcome+0.457
 learn+0.441
 think+0.435
Neg logit contributions
led-0.799
ed-0.661
ied-0.586
y-0.580
les-0.563
Token
Token ID198
Feature activation-8.72e+00

Pos logit contributions
 pleasure+0.073
 Deal+0.059
 great+0.050
 welcome+0.049
 learn+0.047
Neg logit contributions
led-0.132
ed-0.117
y-0.102
les-0.099
es-0.098
Token
Token ID198
Feature activation-8.74e+00

Pos logit contributions
 pleasure+0.374
 Deal+0.294
 welcome+0.229
 OK+0.222
 opinion+0.222
Neg logit contributions
led-0.748
ed-0.641
y-0.591
les-0.583
ied-0.579
TokenL
Token ID43
Feature activation+8.37e+00

Pos logit contributions
 pleasure+0.516
 Deal+0.452
 welcome+0.410
 learn+0.394
 think+0.391
Neg logit contributions
led-0.604
ed-0.492
ied-0.432
y-0.430
les-0.414
Tokenily
Token ID813
Feature activation+1.63e+01

Pos logit contributions
led+0.527
ed+0.420
lers+0.372
ted+0.361
ied+0.361
Neg logit contributions
 pleasure-0.501
 Deal-0.472
 welcome-0.446
 think-0.421
 OK-0.421
Token did
Token ID750
Feature activation+2.41e+00

Pos logit contributions
led+1.135
ed+0.881
ied+0.869
ier+0.827
lers+0.826
Neg logit contributions
 pleasure-0.812
 think-0.733
 learn-0.721
 Deal-0.707
 know-0.698
Token not
Token ID407
Feature activation-1.10e+01

Pos logit contributions
led+0.192
ed+0.160
ied+0.142
es+0.141
ling+0.139
Neg logit contributions
 pleasure-0.112
 Deal-0.092
 welcome-0.078
 meantime-0.069
 Promise-0.067
Token want
Token ID765
Feature activation-1.11e+01

Pos logit contributions
 pleasure+0.384
 Deal+0.304
 Not+0.209
 welcome+0.205
 Today+0.196
Neg logit contributions
led-1.010
ed-0.882
y-0.826
les-0.800
ling-0.796
Token to
Token ID284
Feature activation+4.11e+00

Pos logit contributions
 pleasure+0.626
 Deal+0.540
 welcome+0.507
 learn+0.494
 think+0.483
Neg logit contributions
led-0.801
ed-0.649
ied-0.564
y-0.563
ling-0.559
Token go
Token ID467
Feature activation-6.74e+00

Pos logit contributions
led+0.313
ed+0.271
y+0.263
ier+0.242
ling+0.241
Neg logit contributions
 pleasure-0.179
 Deal-0.161
 Not-0.118
 Today-0.107
 welcome-0.106
Token together
Token ID1978
Feature activation-4.10e+00

Pos logit contributions
led+0.141
ed+0.115
ied+0.103
awed+0.101
we+0.100
Neg logit contributions
 pleasure-0.105
 Deal-0.089
 learn-0.086
 think-0.085
 great-0.084
Token for
Token ID329
Feature activation+1.67e+00

Pos logit contributions
 pleasure+0.242
 Deal+0.205
 welcome+0.197
 learn+0.196
 think+0.193
Neg logit contributions
led-0.280
ed-0.226
ied-0.197
les-0.190
y-0.189
Token a
Token ID257
Feature activation-4.02e+00

Pos logit contributions
led+0.119
ed+0.099
we+0.088
med+0.087
es+0.086
Neg logit contributions
 pleasure-0.078
 Deal-0.076
 Today-0.065
 welcome-0.061
 Not-0.059
Token long
Token ID890
Feature activation-1.82e+00

Pos logit contributions
 Deal+0.193
 pleasure+0.185
 welcome+0.145
 OK+0.139
 Today+0.139
Neg logit contributions
led-0.279
ed-0.234
y-0.233
ling-0.220
ing-0.218
Token time
Token ID640
Feature activation-9.44e+00

Pos logit contributions
 pleasure+0.067
 Deal+0.062
 welcome+0.045
 Okay+0.045
 OK+0.043
Neg logit contributions
led-0.158
ed-0.133
y-0.131
ied-0.125
ling-0.124
Token.
Token ID13
Feature activation+5.91e+00

Pos logit contributions
 pleasure+0.588
 Deal+0.496
 welcome+0.481
 learn+0.471
 think+0.467
Neg logit contributions
led-0.616
ed-0.486
ied-0.433
y-0.412
les-0.409
Token They
Token ID1119
Feature activation-2.08e+00

Pos logit contributions
led+0.423
ed+0.391
ted+0.332
y+0.327
ol+0.326
Neg logit contributions
 pleasure-0.244
 Deal-0.225
 plan-0.209
 deal-0.207
 learn-0.198
Token were
Token ID547
Feature activation+1.09e+00

Pos logit contributions
 pleasure+0.119
 Deal+0.099
 know+0.099
 think+0.099
 learn+0.098
Neg logit contributions
led-0.142
ed-0.115
ied-0.103
we-0.100
ing-0.099
Token all
Token ID477
Feature activation-1.17e+00

Pos logit contributions
led+0.094
ed+0.080
ied+0.073
y+0.072
ling+0.071
Neg logit contributions
 pleasure-0.044
 Deal-0.038
 welcome-0.031
 learn-0.030
 think-0.029
Token very
Token ID845
Feature activation-5.27e+00

Pos logit contributions
 pleasure+0.045
 Deal+0.035
 welcome+0.033
 learn+0.030
 think+0.029
Neg logit contributions
led-0.104
ed-0.089
ied-0.081
y-0.080
les-0.080
Token happy
Token ID3772
Feature activation-1.16e+01

Pos logit contributions
 pleasure+0.149
 Deal+0.111
 welcome+0.091
 learn+0.082
 think+0.079
Neg logit contributions
led-0.518
ed-0.453
ied-0.417
y-0.414
les-0.406
Token it
Token ID340
Feature activation-4.16e+00

Pos logit contributions
led+0.543
ed+0.459
ied+0.413
y+0.412
ling+0.404
Neg logit contributions
 pleasure-0.269
 Deal-0.226
 welcome-0.199
 learn-0.195
 think-0.194
Token a
Token ID257
Feature activation-3.73e+00

Pos logit contributions
 pleasure+0.166
 Deal+0.140
 welcome+0.116
 learn+0.111
 think+0.109
Neg logit contributions
led-0.362
ed-0.310
ied-0.280
y-0.279
les-0.271
Token marble
Token ID30623
Feature activation+5.39e+00

Pos logit contributions
 pleasure+0.186
 Deal+0.184
 Not+0.151
 learn+0.148
 Today+0.145
Neg logit contributions
led-0.234
ed-0.198
y-0.189
web-0.178
lers-0.175
Token?"
Token ID1701
Feature activation-5.34e+00

Pos logit contributions
led+0.445
ed+0.373
ied+0.343
y+0.329
we+0.328
Neg logit contributions
 pleasure-0.231
 Deal-0.193
 welcome-0.187
 learn-0.174
 think-0.173
Token Ben
Token ID3932
Feature activation+1.49e+00

Pos logit contributions
 pleasure+0.312
 Deal+0.263
 welcome+0.236
 deal+0.220
 great+0.219
Neg logit contributions
led-0.361
ed-0.304
y-0.256
ted-0.249
les-0.249
Token asked
Token ID1965
Feature activation+3.06e+00

Pos logit contributions
led+0.108
ed+0.089
ied+0.083
we+0.076
ing+0.076
Neg logit contributions
 pleasure-0.074
 Deal-0.067
 think-0.064
 know-0.063
 learn-0.062
Token.
Token ID13
Feature activation+6.38e+00

Pos logit contributions
led+0.221
ied+0.168
awed+0.166
ed+0.164
lers+0.163
Neg logit contributions
 pleasure-0.141
 welcome-0.133
 Deal-0.133
 OK-0.132
 learn-0.126
Token
Token ID198
Feature activation-8.61e+00

Pos logit contributions
led+0.569
ed+0.511
y+0.456
ied+0.443
ing+0.440
Neg logit contributions
 pleasure-0.235
 Deal-0.181
 welcome-0.146
 learn-0.144
 think-0.133
Token
Token ID198
Feature activation-8.61e+00

Pos logit contributions
 pleasure+0.345
 Deal+0.258
 welcome+0.211
 deal+0.202
 learn+0.196
Neg logit contributions
led-0.751
ed-0.667
y-0.602
ied-0.594
ing-0.593
Token"
Token ID1
Feature activation+2.58e+00

Pos logit contributions
 pleasure+0.399
 Deal+0.357
 welcome+0.314
 learn+0.305
 think+0.299
Neg logit contributions
led-0.686
ed-0.571
ied-0.518
y-0.505
les-0.496
TokenNo
Token ID2949
Feature activation-2.57e+00

Pos logit contributions
led+0.203
ed+0.173
y+0.153
ied+0.153
we+0.148
Neg logit contributions
 pleasure-0.123
 Deal-0.105
 welcome-0.093
 learn-0.088
 OK-0.086
Token all
Token ID477
Feature activation-8.95e-01

Pos logit contributions
led+0.209
ed+0.172
y+0.155
les+0.153
ied+0.152
Neg logit contributions
 pleasure-0.129
 Deal-0.107
 welcome-0.103
 learn-0.102
 know-0.098
Token about
Token ID546
Feature activation+1.91e+00

Pos logit contributions
 pleasure+0.038
 welcome+0.031
 learn+0.029
 know+0.029
 think+0.029
Neg logit contributions
led-0.076
ed-0.066
we-0.059
med-0.056
y-0.056
Token the
Token ID262
Feature activation+3.14e+00

Pos logit contributions
led+0.144
ed+0.120
ied+0.108
y+0.107
les+0.103
Neg logit contributions
 pleasure-0.096
 Deal-0.086
 welcome-0.074
 learn-0.070
 know-0.070
Token mysterious
Token ID11428
Feature activation+1.36e+00

Pos logit contributions
led+0.259
ed+0.221
ied+0.198
y+0.197
les+0.197
Neg logit contributions
 pleasure-0.133
 Deal-0.116
 welcome-0.093
 OK-0.092
 know-0.088
Token math
Token ID10688
Feature activation-4.08e+00

Pos logit contributions
led+0.108
ed+0.090
ied+0.081
y+0.080
ling+0.077
Neg logit contributions
 pleasure-0.066
 Deal-0.056
 welcome-0.051
 learn-0.049
 think-0.048
Token book
Token ID1492
Feature activation+2.86e+00

Pos logit contributions
 pleasure+0.195
 Deal+0.168
 learn+0.164
 think+0.161
 great+0.159
Neg logit contributions
led-0.308
ed-0.255
ied-0.236
y-0.225
ling-0.219
Token.
Token ID13
Feature activation+6.16e+00

Pos logit contributions
led+0.204
ed+0.163
ied+0.147
ling+0.142
ted+0.141
Neg logit contributions
 pleasure-0.147
 learn-0.124
 welcome-0.123
 great-0.122
 think-0.120
Token
Token ID220
Feature activation-1.49e+01

Pos logit contributions
led+0.479
ed+0.445
ted+0.365
ied+0.359
y+0.352
Neg logit contributions
 pleasure-0.238
 Deal-0.223
 deal-0.201
 plan-0.190
 learn-0.184
Token
Token ID198
Feature activation-8.86e+00

Pos logit contributions
 pleasure+0.613
 Deal+0.485
 deal+0.459
 plan+0.411
 learn+0.402
Neg logit contributions
led-1.223
ed-1.139
es-0.981
ied-0.954
ing-0.949
Token
Token ID198
Feature activation-8.85e+00

Pos logit contributions
 pleasure+0.412
 Deal+0.335
 deal+0.283
 opinion+0.258
 OK+0.253
Neg logit contributions
led-0.725
ed-0.646
ied-0.564
es-0.552
y-0.552
TokenThe
Token ID464
Feature activation+6.72e+00

Pos logit contributions
 pleasure+0.469
 Deal+0.404
 welcome+0.359
 learn+0.340
 think+0.340
Neg logit contributions
led-0.664
ed-0.551
ied-0.493
y-0.485
ling-0.472
Token The
Token ID383
Feature activation+2.82e+00

Pos logit contributions
led+0.451
ed+0.420
ted+0.350
ied+0.346
awed+0.335
Neg logit contributions
 pleasure-0.281
 Deal-0.262
 deal-0.213
 learn-0.211
 welcome-0.210
Token spring
Token ID6076
Feature activation-3.14e+00

Pos logit contributions
led+0.198
ed+0.162
ied+0.143
y+0.141
les+0.137
Neg logit contributions
 pleasure-0.162
 Deal-0.144
 welcome-0.128
 learn-0.125
 know-0.123
Token jumped
Token ID11687
Feature activation+7.92e+00

Pos logit contributions
 pleasure+0.148
 welcome+0.129
 great+0.127
 be+0.123
 try+0.123
Neg logit contributions
led-0.208
lers-0.156
ed-0.154
awed-0.153
ling-0.150
Token out
Token ID503
Feature activation+8.20e-01

Pos logit contributions
led+0.548
ed+0.430
ied+0.396
we+0.388
lers+0.378
Neg logit contributions
 pleasure-0.422
 Deal-0.375
 great-0.365
 welcome-0.364
 OK-0.346
Token of
Token ID286
Feature activation+1.35e+01

Pos logit contributions
led+0.061
ed+0.049
ied+0.045
awed+0.044
ils+0.044
Neg logit contributions
 pleasure-0.040
 welcome-0.035
 Deal-0.033
 great-0.033
 OK-0.032
Token the
Token ID262
Feature activation+2.80e+00

Pos logit contributions
led+0.910
ed+0.739
ied+0.680
y+0.663
med+0.646
Neg logit contributions
 pleasure-0.720
 Deal-0.675
 learn-0.584
 Not-0.574
 know-0.563
Token teaspoon
Token ID22326
Feature activation+6.51e+00

Pos logit contributions
led+0.225
ed+0.191
ied+0.168
y+0.165
med+0.164
Neg logit contributions
 pleasure-0.129
 Deal-0.110
 welcome-0.106
 learn-0.098
 great-0.097
Token and
Token ID290
Feature activation-3.75e+00

Pos logit contributions
led+0.525
ed+0.433
ied+0.397
we+0.382
awed+0.380
Neg logit contributions
 pleasure-0.273
 learn-0.228
 think-0.227
 welcome-0.226
 Deal-0.210
Token went
Token ID1816
Feature activation+8.85e+00

Pos logit contributions
 pleasure+0.179
 think+0.146
 see+0.143
 learn+0.142
 welcome+0.142
Neg logit contributions
led-0.277
ed-0.225
ied-0.213
y-0.211
les-0.207
Token very
Token ID845
Feature activation-5.25e+00

Pos logit contributions
led+0.650
ed+0.512
y+0.458
ied+0.457
we+0.444
Neg logit contributions
 pleasure-0.463
 welcome-0.416
 learn-0.400
 Deal-0.391
 see-0.382
Token high
Token ID1029
Feature activation+1.24e+00

Pos logit contributions
 pleasure+0.256
 Deal+0.224
 welcome+0.196
 learn+0.186
 think+0.183
Neg logit contributions
led-0.412
ed-0.345
ied-0.309
y-0.306
ling-0.297
Token of
Token ID286
Feature activation+1.33e+01

Pos logit contributions
led+0.356
ed+0.282
ked+0.246
ied+0.244
les+0.242
Neg logit contributions
 pleasure-0.288
 welcome-0.250
 learn-0.247
 think-0.235
 Deal-0.234
Token his
Token ID465
Feature activation+2.42e+00

Pos logit contributions
led+0.905
ed+0.749
y+0.676
ied+0.664
med+0.656
Neg logit contributions
 pleasure-0.706
 Deal-0.661
 Not-0.540
 OK-0.536
 learn-0.536
Token room
Token ID2119
Feature activation-5.13e+00

Pos logit contributions
led+0.174
ed+0.148
y+0.134
ied+0.128
ing+0.125
Neg logit contributions
 pleasure-0.125
 Deal-0.117
 OK-0.097
 welcome-0.097
 learn-0.094
Token,
Token ID11
Feature activation-5.18e+00

Pos logit contributions
 pleasure+0.289
 welcome+0.237
 Deal+0.234
 learn+0.233
 think+0.226
Neg logit contributions
led-0.352
ed-0.275
ied-0.249
les-0.241
lers-0.240
Token talking
Token ID3375
Feature activation-3.28e+00

Pos logit contributions
 pleasure+0.261
 Deal+0.228
 welcome+0.203
 learn+0.195
 think+0.193
Neg logit contributions
led-0.394
ed-0.328
ied-0.293
y-0.290
les-0.282
Token in
Token ID287
Feature activation+1.22e+01

Pos logit contributions
 pleasure+0.155
 welcome+0.127
 great+0.122
 learn+0.118
 name+0.117
Neg logit contributions
led-0.249
ed-0.197
lers-0.181
awed-0.181
we-0.180
Token quiet
Token ID5897
Feature activation-5.66e+00

Pos logit contributions
led+0.911
ed+0.769
y+0.698
ied+0.685
med+0.676
Neg logit contributions
 pleasure-0.574
 Deal-0.526
 welcome-0.430
 know-0.418
 learn-0.417
Token voices
Token ID10839
Feature activation-3.09e+00

Pos logit contributions
 pleasure+0.298
 welcome+0.246
 Deal+0.242
 learn+0.235
 great+0.229
Neg logit contributions
led-0.403
ed-0.329
ied-0.300
we-0.287
awed-0.286
Token.
Token ID13
Feature activation+5.60e+00

Pos logit contributions
 pleasure+0.159
 welcome+0.132
 learn+0.131
 OK+0.130
 Deal+0.126
Neg logit contributions
led-0.221
ed-0.173
ied-0.158
awed-0.157
lers-0.148
Token They
Token ID1119
Feature activation-2.11e+00

Pos logit contributions
led+0.424
ed+0.380
y+0.320
ied+0.312
ted+0.305
Neg logit contributions
 pleasure-0.255
 Deal-0.235
 welcome-0.196
 deal-0.191
 learn-0.190
Token were
Token ID547
Feature activation+1.20e+00

Pos logit contributions
 pleasure+0.121
 Deal+0.104
 think+0.100
 know+0.100
 learn+0.100
Neg logit contributions
led-0.144
ed-0.116
ied-0.103
we-0.098
les-0.098
Token her
Token ID607
Feature activation+2.50e+00

Pos logit contributions
led+0.916
ed+0.749
ied+0.704
y+0.673
med+0.656
Neg logit contributions
 pleasure-0.727
 Deal-0.661
 Not-0.552
 OK-0.551
 think-0.547
Token hands
Token ID2832
Feature activation-4.25e+00

Pos logit contributions
led+0.192
ed+0.161
ied+0.143
y+0.142
les+0.137
Neg logit contributions
 pleasure-0.125
 Deal-0.110
 welcome-0.097
 learn-0.093
 think-0.091
Token and
Token ID290
Feature activation-3.74e+00

Pos logit contributions
 pleasure+0.204
 Deal+0.159
 welcome+0.154
 learn+0.152
 think+0.152
Neg logit contributions
led-0.324
ed-0.263
les-0.239
we-0.238
ied-0.237
Token crossed
Token ID12606
Feature activation+5.89e+00

Pos logit contributions
 pleasure+0.203
 Deal+0.167
 think+0.167
 learn+0.165
 know+0.161
Neg logit contributions
led-0.257
ed-0.206
ied-0.191
ling-0.188
y-0.187
Token the
Token ID262
Feature activation+2.78e+00

Pos logit contributions
led+0.510
ed+0.428
ied+0.390
y+0.384
lers+0.381
Neg logit contributions
 pleasure-0.233
 Deal-0.184
 welcome-0.175
 learn-0.166
 great-0.165
Token street
Token ID4675
Feature activation-4.78e+00

Pos logit contributions
led+0.223
ed+0.190
ied+0.171
y+0.170
les+0.166
Neg logit contributions
 pleasure-0.129
 Deal-0.112
 welcome-0.094
 OK-0.093
 think-0.091
Token to
Token ID284
Feature activation+4.27e+00

Pos logit contributions
 pleasure+0.261
 Deal+0.217
 learn+0.215
 welcome+0.210
 think+0.207
Neg logit contributions
led-0.344
ed-0.274
ied-0.250
les-0.238
ted-0.234
Token get
Token ID651
Feature activation-1.00e+01

Pos logit contributions
led+0.304
ed+0.257
les+0.229
y+0.228
ted+0.226
Neg logit contributions
 pleasure-0.187
 Deal-0.182
 Not-0.147
 Today-0.146
 OK-0.133
Token to
Token ID284
Feature activation+4.30e+00

Pos logit contributions
 pleasure+0.484
 welcome+0.389
 Deal+0.384
 OK+0.376
 great+0.372
Neg logit contributions
led-0.758
ed-0.618
y-0.587
les-0.576
ied-0.560
Token the
Token ID262
Feature activation+3.06e+00

Pos logit contributions
led+0.242
ed+0.197
les+0.179
y+0.174
ted+0.173
Neg logit contributions
 Deal-0.235
 pleasure-0.219
 Today-0.183
 Not-0.181
 Okay-0.168
Token park
Token ID3952
Feature activation-8.46e+00

Pos logit contributions
led+0.251
ed+0.214
ied+0.191
y+0.191
les+0.186
Neg logit contributions
 pleasure-0.134
 Deal-0.118
 welcome-0.097
 know-0.094
 learn-0.094
Token went
Token ID1816
Feature activation+8.95e+00

Pos logit contributions
 pleasure+0.161
 be+0.150
 have+0.149
 see+0.145
 think+0.136
Neg logit contributions
led-0.253
ins-0.205
lers-0.201
ils-0.201
awed-0.197
Token away
Token ID1497
Feature activation+9.27e-01

Pos logit contributions
led+0.627
ed+0.501
ied+0.451
we+0.445
y+0.438
Neg logit contributions
 pleasure-0.477
 welcome-0.425
 great-0.399
 learn-0.395
 Deal-0.394
Token,
Token ID11
Feature activation-5.02e+00

Pos logit contributions
led+0.070
ed+0.057
ied+0.053
les+0.051
y+0.050
Neg logit contributions
 pleasure-0.047
 Deal-0.038
 welcome-0.038
 learn-0.036
 think-0.036
Token and
Token ID290
Feature activation-3.82e+00

Pos logit contributions
 pleasure+0.260
 Deal+0.242
 welcome+0.202
 learn+0.194
 know+0.192
Neg logit contributions
led-0.373
ed-0.309
ied-0.272
y-0.271
ling-0.268
Token the
Token ID262
Feature activation+2.70e+00

Pos logit contributions
 pleasure+0.166
 Deal+0.136
 welcome+0.124
 learn+0.118
 think+0.117
Neg logit contributions
led-0.316
ed-0.268
ied-0.243
y-0.241
les-0.236
Token little
Token ID1310
Feature activation-2.40e+00

Pos logit contributions
led+0.211
ed+0.178
ied+0.157
ling+0.156
y+0.155
Neg logit contributions
 pleasure-0.125
 Deal-0.115
 welcome-0.092
 think-0.092
 learn-0.091
Token car
Token ID1097
Feature activation+2.00e+00

Pos logit contributions
 pleasure+0.118
 Deal+0.094
 welcome+0.092
 great+0.086
 learn+0.085
Neg logit contributions
led-0.190
ed-0.157
ied-0.145
y-0.137
med-0.137
Token drove
Token ID10357
Feature activation+1.14e+01

Pos logit contributions
led+0.131
ed+0.102
ied+0.100
we+0.097
y+0.095
Neg logit contributions
 pleasure-0.103
 learn-0.090
 know-0.088
 think-0.087
 see-0.086
Token out
Token ID503
Feature activation+1.17e+00

Pos logit contributions
led+0.762
ed+0.613
ied+0.538
y+0.532
les+0.514
Neg logit contributions
 pleasure-0.692
 Deal-0.608
 welcome-0.566
 learn-0.548
 think-0.540
Token of
Token ID286
Feature activation+1.35e+01

Pos logit contributions
led+0.080
ed+0.063
awed+0.057
ied+0.056
y+0.055
Neg logit contributions
 pleasure-0.068
 welcome-0.058
 learn-0.055
 know-0.055
 Deal-0.054
Token the
Token ID262
Feature activation+2.74e+00

Pos logit contributions
led+0.949
ed+0.769
ied+0.699
y+0.691
ted+0.664
Neg logit contributions
 pleasure-0.702
 Deal-0.667
 learn-0.545
 Not-0.544
 welcome-0.530
Tokenily
Token ID813
Feature activation+1.72e+01

Pos logit contributions
led+0.545
ed+0.423
y+0.366
ied+0.361
lers+0.359
Neg logit contributions
 pleasure-0.595
 Deal-0.557
 welcome-0.518
 learn-0.497
 OK-0.495
Token says
Token ID1139
Feature activation-1.56e+00

Pos logit contributions
led+1.265
ed+1.049
ied+0.927
y+0.919
les+0.893
Neg logit contributions
 pleasure-0.919
 Deal-0.807
 welcome-0.723
 learn-0.695
 think-0.686
Token,
Token ID11
Feature activation-4.07e+00

Pos logit contributions
 pleasure+0.061
 Deal+0.051
 welcome+0.046
 OK+0.043
 learn+0.042
Neg logit contributions
led-0.136
ed-0.113
ied-0.105
y-0.103
les-0.102
Token "
Token ID366
Feature activation+7.21e-01

Pos logit contributions
 pleasure+0.161
 Deal+0.136
 welcome+0.116
 learn+0.109
 think+0.107
Neg logit contributions
led-0.355
ed-0.303
ied-0.276
y-0.273
les-0.267
TokenOK
Token ID11380
Feature activation-3.45e+00

Pos logit contributions
led+0.051
ed+0.044
we+0.038
y+0.037
ted+0.037
Neg logit contributions
 pleasure-0.040
 Deal-0.034
 welcome-0.030
 know-0.029
 learn-0.029
Token,
Token ID11
Feature activation-4.03e+00

Pos logit contributions
 pleasure+0.214
 Deal+0.186
 know+0.165
 Not+0.165
 learn+0.163
Neg logit contributions
led-0.194
ed-0.169
y-0.151
ing-0.149
ier-0.140
Token Tom
Token ID4186
Feature activation-1.11e+00

Pos logit contributions
 pleasure+0.192
 Deal+0.169
 Today+0.148
 learn+0.141
 know+0.141
Neg logit contributions
led-0.246
ed-0.215
ly-0.194
ted-0.193
ing-0.190
Token.
Token ID13
Feature activation+7.33e+00

Pos logit contributions
 pleasure+0.064
 welcome+0.057
 Deal+0.057
 OK+0.054
 think+0.053
Neg logit contributions
led-0.076
ed-0.060
ied-0.056
med-0.053
we-0.051
Token But
Token ID887
Feature activation-1.17e+01

Pos logit contributions
led+0.484
ed+0.468
als+0.393
ted+0.382
es+0.371
Neg logit contributions
 pleasure-0.318
 Deal-0.282
 great-0.278
 plan-0.277
 know-0.273
Token don
Token ID836
Feature activation-1.42e+01

Pos logit contributions
 pleasure+0.519
 Deal+0.468
 know+0.379
 Today+0.377
 learn+0.372
Neg logit contributions
led-0.864
ed-0.744
we-0.678
ied-0.671
ing-0.666
Token't
Token ID470
Feature activation-2.30e+00

Pos logit contributions
 pleasure+0.643
 Deal+0.473
 welcome+0.420
 think+0.390
 opinion+0.372
Neg logit contributions
led-1.180
ed-1.010
y-0.913
ing-0.912
ied-0.912
Token
Token ID198
Feature activation-8.79e+00

Pos logit contributions
 pleasure+0.347
 Deal+0.282
 welcome+0.214
 deal+0.211
 OK+0.207
Neg logit contributions
led-0.747
ed-0.660
ied-0.603
y-0.596
es-0.588
TokenMike
Token ID16073
Feature activation+5.82e+00

Pos logit contributions
 pleasure+0.457
 Deal+0.393
 welcome+0.347
 learn+0.331
 think+0.329
Neg logit contributions
led-0.657
ed-0.552
ied-0.492
y-0.488
med-0.471
Token had
Token ID550
Feature activation+8.95e+00

Pos logit contributions
led+0.382
ed+0.308
ier+0.293
ied+0.288
we+0.281
Neg logit contributions
 pleasure-0.267
 think-0.263
 know-0.262
 learn-0.247
 -0.241
Token to
Token ID284
Feature activation+4.16e+00

Pos logit contributions
led+0.683
ed+0.587
ied+0.514
y+0.499
med+0.488
Neg logit contributions
 pleasure-0.434
 Deal-0.391
 welcome-0.335
 Today-0.313
 learn-0.309
Token act
Token ID719
Feature activation-3.54e+00

Pos logit contributions
led+0.308
ed+0.260
y+0.232
ied+0.230
ling+0.228
Neg logit contributions
 pleasure-0.184
 Deal-0.157
 Not-0.130
 Today-0.123
 Okay-0.121
Token fast
Token ID3049
Feature activation+7.57e-01

Pos logit contributions
 pleasure+0.169
 Deal+0.143
 welcome+0.132
 learn+0.126
 think+0.125
Neg logit contributions
led-0.278
ed-0.231
ied-0.209
y-0.208
les-0.202
Token.
Token ID13
Feature activation+5.94e+00

Pos logit contributions
led+0.060
ed+0.048
ied+0.045
we+0.044
awed+0.043
Neg logit contributions
 pleasure-0.035
 Deal-0.027
 welcome-0.027
 learn-0.026
 think-0.026
Token He
Token ID679
Feature activation+2.73e+00

Pos logit contributions
led+0.403
ed+0.364
ied+0.307
y+0.304
ing+0.300
Neg logit contributions
 pleasure-0.294
 Deal-0.272
 welcome-0.233
 learn-0.233
 great-0.225
Token grabbed
Token ID13176
Feature activation+9.67e+00

Pos logit contributions
led+0.175
ed+0.138
ied+0.127
ier+0.122
ing+0.122
Neg logit contributions
 pleasure-0.160
 think-0.138
 know-0.136
 Deal-0.136
 learn-0.134
Token a
Token ID257
Feature activation-3.87e+00

Pos logit contributions
led+0.764
ed+0.648
ied+0.576
y+0.563
les+0.554
Neg logit contributions
 pleasure-0.461
 Deal-0.404
 welcome-0.350
 learn-0.338
 think-0.329
Token tall
Token ID7331
Feature activation+3.74e+00

Pos logit contributions
 pleasure+0.209
 Deal+0.188
 welcome+0.159
 learn+0.158
 OK+0.155
Neg logit contributions
led-0.272
ed-0.227
y-0.205
ied-0.198
ling-0.196
Token them
Token ID606
Feature activation-2.99e+00

Pos logit contributions
 pleasure+0.678
 Deal+0.570
 welcome+0.518
 learn+0.493
 think+0.487
Neg logit contributions
led-1.194
ed-0.998
ied-0.896
y-0.888
ling-0.870
Token.
Token ID13
Feature activation+6.51e+00

Pos logit contributions
 pleasure+0.169
 Deal+0.147
 welcome+0.136
 learn+0.133
 think+0.131
Neg logit contributions
led-0.211
ed-0.173
ied-0.152
y-0.148
les-0.145
Token She
Token ID1375
Feature activation+3.54e+00

Pos logit contributions
led+0.401
ed+0.365
y+0.313
ted+0.305
med+0.298
Neg logit contributions
 pleasure-0.343
 Deal-0.299
 deal-0.279
 great-0.279
 welcome-0.279
Token said
Token ID531
Feature activation+1.35e+00

Pos logit contributions
led+0.234
ed+0.188
ied+0.167
y+0.161
ling+0.160
Neg logit contributions
 pleasure-0.210
 Deal-0.180
 think-0.173
 learn-0.173
 welcome-0.172
Token,
Token ID11
Feature activation-4.41e+00

Pos logit contributions
led+0.109
ed+0.091
ied+0.082
y+0.081
les+0.080
Neg logit contributions
 pleasure-0.063
 Deal-0.053
 welcome-0.048
 learn-0.046
 think-0.045
Token "
Token ID366
Feature activation+5.91e-02

Pos logit contributions
 pleasure+0.204
 Deal+0.173
 welcome+0.152
 learn+0.145
 know+0.143
Neg logit contributions
led-0.347
ed-0.302
y-0.265
ied-0.265
ing-0.258
TokenIt
Token ID1026
Feature activation-7.10e-03

Pos logit contributions
led+0.004
ed+0.004
ied+0.003
y+0.003
les+0.003
Neg logit contributions
 pleasure-0.003
 Deal-0.003
 welcome-0.002
 learn-0.002
 think-0.002
Token's
Token ID338
Feature activation+5.18e+00

Pos logit contributions
 pleasure+0.000
 Deal+0.000
 welcome+0.000
 learn+0.000
 think+0.000
Neg logit contributions
led-0.000
ed-0.000
ied-0.000
y-0.000
les-0.000
Token so
Token ID523
Feature activation-1.00e+01

Pos logit contributions
led+0.388
ed+0.316
y+0.315
ied+0.307
ling+0.289
Neg logit contributions
 pleasure-0.197
 Deal-0.183
 learn-0.156
 Many-0.146
 know-0.145
Token great
Token ID1049
Feature activation-9.84e+00

Pos logit contributions
 pleasure+0.375
 Deal+0.330
 learn+0.246
 welcome+0.246
 OK+0.238
Neg logit contributions
led-0.892
ed-0.757
ied-0.693
y-0.690
ling-0.672
Token that
Token ID326
Feature activation+1.26e+00

Pos logit contributions
 pleasure+0.541
 Deal+0.446
 welcome+0.431
 think+0.405
 great+0.402
Neg logit contributions
led-0.720
ed-0.585
ied-0.529
y-0.514
ling-0.510
Token know
Token ID760
Feature activation-1.82e+01

Pos logit contributions
 pleasure+0.108
 Deal+0.090
 welcome+0.059
 Not+0.056
 Today+0.053
Neg logit contributions
led-0.294
ed-0.258
y-0.244
ling-0.233
ied-0.232
Token what
Token ID644
Feature activation-9.77e+00

Pos logit contributions
 pleasure+0.796
 Deal+0.660
 welcome+0.593
 learn+0.562
 OK+0.561
Neg logit contributions
led-1.518
ed-1.284
ied-1.147
y-1.142
ling-1.116
Token to
Token ID284
Feature activation+3.95e+00

Pos logit contributions
 pleasure+0.532
 Deal+0.454
 welcome+0.432
 learn+0.419
 think+0.414
Neg logit contributions
led-0.712
ed-0.580
ied-0.510
y-0.504
les-0.499
Token expect
Token ID1607
Feature activation-4.54e+00

Pos logit contributions
led+0.331
ed+0.285
y+0.275
ied+0.262
ly+0.258
Neg logit contributions
 pleasure-0.158
 Deal-0.133
 welcome-0.090
 Not-0.088
 Sometimes-0.086
Token.
Token ID13
Feature activation+5.69e+00

Pos logit contributions
 pleasure+0.274
 Deal+0.238
 welcome+0.233
 learn+0.225
 OK+0.223
Neg logit contributions
led-0.300
ed-0.234
ied-0.204
ling-0.202
y-0.202
Token But
Token ID887
Feature activation-1.27e+01

Pos logit contributions
led+0.427
ed+0.400
ted+0.333
y+0.329
ly+0.327
Neg logit contributions
 pleasure-0.242
 Deal-0.209
 welcome-0.190
 plan-0.174
 deal-0.172
Token her
Token ID607
Feature activation+2.39e+00

Pos logit contributions
 pleasure+0.683
 Deal+0.606
 welcome+0.539
 learn+0.515
 think+0.510
Neg logit contributions
led-0.929
ed-0.771
ied-0.682
y-0.674
les-0.648
Token mom
Token ID1995
Feature activation-6.56e+00

Pos logit contributions
led+0.211
ed+0.184
ied+0.166
y+0.164
ing+0.158
Neg logit contributions
 pleasure-0.086
 Deal-0.072
 welcome-0.062
 think-0.054
 know-0.053
Tokenmy
Token ID1820
Feature activation-3.51e+00

Pos logit contributions
 pleasure+0.304
 think+0.265
 learn+0.261
 know+0.261
 Deal+0.257
Neg logit contributions
led-0.488
ed-0.398
ied-0.355
lers-0.353
we-0.350
Token held
Token ID2714
Feature activation+8.27e+00

Pos logit contributions
 pleasure+0.175
 think+0.149
 Deal+0.148
 know+0.146
 learn+0.146
Neg logit contributions
led-0.254
ed-0.206
ied-0.187
we-0.182
lers-0.181
Token her
Token ID607
Feature activation+2.41e+00

Pos logit contributions
led+0.610
ed+0.501
ied+0.448
y+0.446
les+0.432
Neg logit contributions
 pleasure-0.436
 Deal-0.386
 welcome-0.347
 learn-0.331
 think-0.328
Token day
Token ID1110
Feature activation-5.99e+00

Pos logit contributions
led+0.207
ed+0.178
y+0.176
ied+0.163
ing+0.158
Neg logit contributions
 pleasure-0.151
 Deal-0.143
 OK-0.114
 welcome-0.110
 know-0.109
Token,
Token ID11
Feature activation-5.09e+00

Pos logit contributions
 pleasure+0.254
 Deal+0.210
 welcome+0.189
 learn+0.176
 think+0.173
Neg logit contributions
led-0.505
ed-0.425
ied-0.388
y-0.380
les-0.376
Token Lucy
Token ID22162
Feature activation-1.48e+00

Pos logit contributions
 pleasure+0.246
 Deal+0.225
 welcome+0.188
 learn+0.187
 know+0.182
Neg logit contributions
led-0.393
ed-0.327
y-0.295
ied-0.291
ted-0.280
Token would
Token ID561
Feature activation+6.54e+00

Pos logit contributions
 pleasure+0.072
 learn+0.068
 think+0.067
 know+0.065
 see+0.064
Neg logit contributions
led-0.103
ed-0.082
ied-0.078
ier-0.074
med-0.073
Token take
Token ID1011
Feature activation-2.22e+00

Pos logit contributions
led+0.490
ed+0.416
y+0.402
ied+0.385
ling+0.377
Neg logit contributions
 pleasure-0.281
 Deal-0.261
 OK-0.192
 Okay-0.188
 welcome-0.186
Token care
Token ID1337
Feature activation-1.54e+01

Pos logit contributions
 pleasure+0.104
 Deal+0.096
 welcome+0.077
 OK+0.075
 think+0.075
Neg logit contributions
led-0.176
ed-0.152
ied-0.132
y-0.130
les-0.130
Token of
Token ID286
Feature activation+1.32e+01

Pos logit contributions
 pleasure+0.900
 welcome+0.795
 learn+0.767
 Deal+0.751
 know+0.749
Neg logit contributions
led-1.008
ed-0.784
awed-0.704
lers-0.679
ted-0.674
Token the
Token ID262
Feature activation+2.43e+00

Pos logit contributions
led+0.912
ed+0.747
ied+0.681
y+0.663
les+0.654
Neg logit contributions
 pleasure-0.707
 Deal-0.675
 welcome-0.553
 Today-0.544
 OK-0.531
Token da
Token ID12379
Feature activation+7.57e+00

Pos logit contributions
led+0.137
ed+0.108
y+0.094
ied+0.092
les+0.088
Neg logit contributions
 pleasure-0.166
 Deal-0.157
 welcome-0.137
 OK-0.135
 learn-0.133
Tokenisy
Token ID13560
Feature activation+8.55e+00

Pos logit contributions
led+0.485
ed+0.403
y+0.339
ied+0.332
med+0.317
Neg logit contributions
 pleasure-0.449
 Deal-0.387
 welcome-0.375
 learn-0.369
 great-0.361
Token.
Token ID13
Feature activation+5.79e+00

Pos logit contributions
led+0.607
ed+0.495
ied+0.430
med+0.415
awed+0.415
Neg logit contributions
 pleasure-0.476
 learn-0.394
 Deal-0.388
 welcome-0.386
 think-0.378
Token some
Token ID617
Feature activation-4.01e+00

Pos logit contributions
 pleasure+0.210
 welcome+0.176
 Deal+0.170
 great+0.169
 learn+0.167
Neg logit contributions
led-0.254
ed-0.204
ied-0.192
y-0.185
awed-0.177
Token more
Token ID517
Feature activation-2.29e+00

Pos logit contributions
 pleasure+0.190
 Deal+0.157
 welcome+0.149
 learn+0.141
 great+0.138
Neg logit contributions
led-0.319
ed-0.271
ied-0.242
y-0.239
we-0.228
Token pretty
Token ID2495
Feature activation-2.17e+00

Pos logit contributions
 pleasure+0.129
 Deal+0.110
 welcome+0.105
 learn+0.102
 know+0.100
Neg logit contributions
led-0.161
ed-0.133
ied-0.117
y-0.114
we-0.109
Token pictures
Token ID5986
Feature activation+8.91e-01

Pos logit contributions
 pleasure+0.108
 learn+0.084
 welcome+0.084
 fun+0.083
 great+0.082
Neg logit contributions
led-0.152
ed-0.127
ied-0.121
awed-0.111
ked-0.109
Token.
Token ID13
Feature activation+6.21e+00

Pos logit contributions
led+0.062
ed+0.049
ied+0.045
awed+0.045
ling+0.043
Neg logit contributions
 pleasure-0.047
 welcome-0.040
 learn-0.038
 fun-0.037
 have-0.036
Token
Token ID220
Feature activation-1.49e+01

Pos logit contributions
led+0.470
ed+0.431
y+0.387
ted+0.383
med+0.374
Neg logit contributions
 pleasure-0.228
 Deal-0.206
 deal-0.178
 learn-0.174
 great-0.173
Token
Token ID198
Feature activation-9.01e+00

Pos logit contributions
 pleasure+0.566
 Deal+0.466
 deal+0.390
 think+0.373
 learn+0.372
Neg logit contributions
led-1.284
ed-1.158
ied-1.033
y-1.020
es-1.011
Token
Token ID198
Feature activation-9.01e+00

Pos logit contributions
 pleasure+0.382
 Deal+0.322
 deal+0.253
 welcome+0.249
 OK+0.244
Neg logit contributions
led-0.730
ed-0.642
ied-0.596
y-0.593
we-0.582
TokenThe
Token ID464
Feature activation+6.74e+00

Pos logit contributions
 pleasure+0.469
 Deal+0.403
 welcome+0.352
 OK+0.328
 think+0.327
Neg logit contributions
led-0.651
ed-0.549
ied-0.511
y-0.506
we-0.495
Token End
Token ID5268
Feature activation-4.89e+00

Pos logit contributions
led+0.518
ed+0.431
ied+0.384
y+0.383
les+0.380
Neg logit contributions
 pleasure-0.320
 Deal-0.292
 welcome-0.241
 know-0.238
 OK-0.235
Token.
Token ID13
Feature activation+5.99e+00

Pos logit contributions
 pleasure+0.272
 Deal+0.242
 welcome+0.213
 learn+0.207
 think+0.204
Neg logit contributions
led-0.343
ed-0.286
y-0.250
ied-0.248
les-0.239
Token and
Token ID290
Feature activation-3.89e+00

Pos logit contributions
 pleasure+0.276
 welcome+0.210
 think+0.191
 learn+0.191
 Deal+0.190
Neg logit contributions
led-0.537
ed-0.428
ied-0.410
ling-0.393
les-0.388
Token showed
Token ID3751
Feature activation+5.37e+00

Pos logit contributions
 pleasure+0.211
 Deal+0.172
 welcome+0.171
 great+0.166
 learn+0.165
Neg logit contributions
led-0.277
ed-0.228
y-0.204
les-0.204
ied-0.203
Token them
Token ID606
Feature activation-4.04e+00

Pos logit contributions
led+0.465
ed+0.386
we+0.359
awed+0.355
ling+0.353
Neg logit contributions
 pleasure-0.193
 welcome-0.140
 great-0.137
 know-0.134
 learn-0.134
Token how
Token ID703
Feature activation-5.77e+00

Pos logit contributions
 pleasure+0.181
 Deal+0.148
 learn+0.147
 know+0.140
 welcome+0.140
Neg logit contributions
led-0.329
ed-0.267
ied-0.242
y-0.241
ling-0.239
Token to
Token ID284
Feature activation+3.90e+00

Pos logit contributions
 pleasure+0.293
 welcome+0.234
 great+0.227
 learn+0.226
 know+0.225
Neg logit contributions
led-0.441
ed-0.363
les-0.329
y-0.325
ied-0.319
Token count
Token ID954
Feature activation-1.14e+01

Pos logit contributions
led+0.323
ed+0.273
y+0.254
ied+0.247
les+0.246
Neg logit contributions
 pleasure-0.161
 Deal-0.138
 OK-0.107
 welcome-0.105
 Not-0.101
Token it
Token ID340
Feature activation-4.57e+00

Pos logit contributions
 pleasure+0.599
 Deal+0.495
 welcome+0.485
 learn+0.468
 great+0.466
Neg logit contributions
led-0.835
ed-0.672
ied-0.599
ling-0.579
awed-0.572
Token.
Token ID13
Feature activation+5.79e+00

Pos logit contributions
 pleasure+0.250
 Deal+0.216
 welcome+0.208
 learn+0.207
 think+0.204
Neg logit contributions
led-0.318
ed-0.250
ied-0.231
ling-0.217
awed-0.216
Token
Token ID220
Feature activation-1.52e+01

Pos logit contributions
led+0.474
ed+0.420
y+0.362
ied+0.362
ted+0.361
Neg logit contributions
 pleasure-0.245
 Deal-0.208
 welcome-0.180
 learn-0.175
 think-0.174
Token
Token ID198
Feature activation-9.16e+00

Pos logit contributions
 pleasure+0.566
 Deal+0.446
 deal+0.376
 learn+0.371
 welcome+0.363
Neg logit contributions
led-1.324
ed-1.202
ied-1.059
y-1.051
es-1.046
Token
Token ID198
Feature activation-9.15e+00

Pos logit contributions
 pleasure+0.399
 Deal+0.311
 deal+0.250
 welcome+0.249
 opinion+0.237
Neg logit contributions
led-0.773
ed-0.683
y-0.626
ied-0.613
med-0.603
Token that
Token ID326
Feature activation+7.97e-01

Pos logit contributions
 pleasure+0.048
 Deal+0.042
 welcome+0.037
 learn+0.036
 think+0.035
Neg logit contributions
led-0.075
ed-0.063
ied-0.056
y-0.056
les-0.054
Token your
Token ID534
Feature activation-6.62e+00

Pos logit contributions
led+0.063
ed+0.053
ied+0.047
y+0.047
les+0.046
Neg logit contributions
 pleasure-0.038
 Deal-0.033
 welcome-0.028
 learn-0.027
 think-0.027
Token snow
Token ID6729
Feature activation-2.61e+00

Pos logit contributions
 pleasure+0.308
 Deal+0.295
 Not+0.241
 welcome+0.240
 learn+0.238
Neg logit contributions
led-0.473
ed-0.396
y-0.357
lers-0.355
ling-0.348
Tokenmen
Token ID3653
Feature activation+1.11e+01

Pos logit contributions
 pleasure+0.142
 Deal+0.124
 welcome+0.114
 learn+0.109
 think+0.109
Neg logit contributions
led-0.186
ed-0.153
ied-0.137
y-0.133
les-0.129
Token are
Token ID389
Feature activation-6.61e+00

Pos logit contributions
led+0.937
ed+0.797
ied+0.720
y+0.717
les+0.698
Neg logit contributions
 pleasure-0.465
 Deal-0.396
 welcome-0.336
 learn-0.318
 think-0.312
Token not
Token ID407
Feature activation-1.09e+01

Pos logit contributions
 pleasure+0.254
 Deal+0.211
 welcome+0.181
 learn+0.170
 think+0.167
Neg logit contributions
led-0.584
ed-0.501
ied-0.455
y-0.451
les-0.440
Token food
Token ID2057
Feature activation-2.88e+00

Pos logit contributions
 pleasure+0.506
 Deal+0.426
 welcome+0.391
 OK+0.366
 learn+0.366
Neg logit contributions
led-0.870
ed-0.737
ied-0.660
y-0.645
les-0.635
Token.
Token ID13
Feature activation+6.47e+00

Pos logit contributions
 pleasure+0.171
 Deal+0.152
 welcome+0.142
 learn+0.136
 think+0.135
Neg logit contributions
led-0.192
ed-0.156
ied-0.137
y-0.132
med-0.129
Token He
Token ID679
Feature activation+2.86e+00

Pos logit contributions
led+0.393
ed+0.357
es+0.312
y+0.295
we+0.292
Neg logit contributions
 pleasure-0.329
 plan-0.282
 great-0.269
 compromise-0.265
 learn-0.264
Token knows
Token ID4206
Feature activation-9.45e-01

Pos logit contributions
led+0.223
ed+0.188
ied+0.170
y+0.167
les+0.161
Neg logit contributions
 pleasure-0.136
 Deal-0.117
 welcome-0.105
 learn-0.102
 think-0.101
Token that
Token ID326
Feature activation+8.13e-01

Pos logit contributions
 pleasure+0.046
 Deal+0.040
 welcome+0.035
 learn+0.034
 think+0.033
Neg logit contributions
led-0.074
ed-0.062
ied-0.055
y-0.055
les-0.053